© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29483
    Prev
    Next
    INDEX
    Explanations

    comparison analysis

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

    internal states and social interactions

    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
     P
    0.59
     Beatriz
    0.59
     Hernández
    0.58
     Pérez
    0.58
     Kasper
    0.57
     Rodríguez
    0.55
     Kass
    0.55
     Muñoz
    0.55
     Kaplan
    0.54
     Verona
    0.54
    POSITIVE LOGITS
     вашу
    0.44
    luence
    0.43
    偏
    0.42
     দারুণ
    0.42
     escog
    0.42
    NaOMe
    0.42
    leftarrow
    0.42
     समझे
    0.41
     वंचित
    0.41
    +".
    0.41
    Activations Density 0.000%

    No Known Activations