© 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. 95391
    Prev
    Next
    INDEX
    Explanations

    time indicators

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

    reality

    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
    w
    0.54
    1
    0.49
    m
    0.48
    c
    0.46
    y
    0.46
    ج
    0.44
    ↵
    0.43
    布
    0.43
    W
    0.42
    t
    0.42
    POSITIVE LOGITS
    اردوش
    0.59
     输出
    0.55
     ശബ്
    0.55
     बलिदान
    0.55
     представлены
    0.54
     grün
    0.54
    spacePad
    0.53
     Förderung
    0.52
    壴
    0.52
     frequência
    0.52
    Activations Density 0.000%

    No Known Activations