© 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. 48844
    Prev
    Next
    INDEX
    Explanations

    specifically to implement

    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
     семье
    0.52
     pierde
    0.52
     टोटल
    0.50
    ệng
    0.49
     dimes
    0.46
    퇴
    0.46
     gió
    0.46
     прибыль
    0.46
     खाते
    0.46
     कुल
    0.45
    POSITIVE LOGITS
     Beispiel
    0.53
     deren
    0.48
     Mac
    0.47
    णियों
    0.46
    in
    0.45
    ',()=>{
    0.45
    ",
    0.44
     Organisations
    0.44
     tám
    0.44
     Ra
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.