© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 211229
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and code"}, {"tokens": ["returns</b>", ":", "</b>", "\n", "<br", "</b>", ":"], "explanation": "end of docstrings"}, {"tokens": ["Returns", ":"], "explanation": "docstring return types"}, {"tokens": ["\"", "}"], "explanation": "closing quotes or braces"}, {"tokens": ["```"], "explanation": "code blocks"}, {"tokens": ["."], "explanation": "end of sentence or code"}, {"tokens": ["(float)", ":", "The", "price"], "explanation": "return type hints"}]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     énon
    0.93
     erythrocytes
    0.84
     autocl
    0.84
     exerce
    0.82
     étudiants
    0.80
     enzim
    0.80
     accessoires
    0.80
     étaient
    0.79
     aloe
    0.79
     saws
    0.79
    POSITIVE LOGITS
    is
    0.91
    ↵
    0.78
    ka
    0.75
    isinin
    0.68
    il
    0.68
    ρι
    0.64
    ino
    0.63
    ke
    0.63
    览
    0.61
    ate
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.