© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43434
    Prev
    Next
    INDEX
    Explanations

    hollow, Its, Execution, stay

    np_acts-logits-general · gemini-2.5-flash-lite

    relatively abundant

    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
    ه
    0.44
     paragraphs
    0.44
    历
    0.43
     goog
    0.43
     Rom
    0.43
     elimina
    0.43
     proof
    0.42
     Surgery
    0.42
     medis
    0.42
     elimin
    0.41
    POSITIVE LOGITS
    "?:
    0.45
    ohi
    0.45
    шай
    0.45
     ক্রিকে
    0.44
     جنيه
    0.44
     Льво
    0.43
    onDidChange
    0.42
    isième
    0.42
    charCode
    0.41
    的山
    0.41
    Activations Density 0.000%

    No Known Activations