© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76160
    Prev
    Next
    INDEX
    Explanations

    illustrations and sketch

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

    password files

    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
     gaat
    0.46
    这次
    0.44
     মাথায়
    0.44
     l
    0.43
    <0xB1>
    0.42
     gik
    0.42
    妨
    0.42
    (*
    0.41
     handelt
    0.41
     osoby
    0.41
    POSITIVE LOGITS
     petición
    0.49
    ान्त
    0.47
     depósito
    0.45
    İK
    0.45
     फार्मा
    0.45
    હિતી
    0.44
    ObjData
    0.44
    пресс
    0.44
    รม
    0.44
    녕하십니까
    0.43
    Activations Density 0.000%

    No Known Activations