© 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. 233740
    Prev
    Next
    INDEX
    Explanations

    Specific nouns and keywords

    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
    ↵
    0.49
    Privacy
    0.43
    av
    0.43
    aq
    0.42
    name
    0.42
    behav
    0.42
    मि
    0.41
    status
    0.41
    ావ
    0.41
    ]^
    0.40
    POSITIVE LOGITS
     uko
    0.50
     ilan
    0.50
    ुद्ध
    0.48
     utterly
    0.48
     Adolf
    0.47
     abat
    0.46
     odw
    0.46
    寢
    0.46
     കാര്‍
    0.46
     matematik
    0.45
    Activations Density 0.001%

    No Known Activations