© 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. 68314
    Prev
    Next
    INDEX
    Explanations

    any or other

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

    Flask app.py

    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
    ant
    0.57
     employee
    0.55
     time
    0.55
    5
    0.53
    rm
    0.52
    8
    0.51
    ad
    0.50
     way
    0.50
     occupational
    0.50
    ;
    0.50
    POSITIVE LOGITS
     bahsede
    0.58
     ప్రాంత
    0.56
     കുടും
    0.55
     wollten
    0.55
     യൂണി
    0.54
    𝓽
    0.54
     بيت
    0.53
     Familie
    0.52
     ovipares
    0.52
    <unused2016>
    0.52
    Activations Density 0.000%

    No Known Activations