© 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. 225908
    Prev
    Next
    INDEX
    Explanations

    finding words like missing or experience

    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
    ubhav
    0.49
     घेणे
    0.49
    Ҳ
    0.48
    ays
    0.47
    햐
    0.46
    ئی
    0.46
    otek
    0.46
    esehatan
    0.46
    isl
    0.45
    ladı
    0.45
    POSITIVE LOGITS
     {:
    0.46
     '+
    0.44
     '|
    0.43
     長
    0.43
     Lon
    0.43
     '%
    0.42
     [-
    0.42
     $.
    0.41
     htonl
    0.41
     Hopefully
    0.41
    Activations Density 0.000%

    No Known Activations