© 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. 11205
    Prev
    Next
    INDEX
    Explanations

    the authority

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

    about Jesus

    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
    ሱስ
    0.46
    Q
    0.46
    格
    0.45
    ToLower
    0.44
    غ
    0.44
    K
    0.44
    asList
    0.43
    QUrl
    0.43
    Ease
    0.42
    B
    0.42
    POSITIVE LOGITS
     eyeglasses
    0.50
     ojos
    0.49
     पादुकोण
    0.47
     ตา
    0.46
     ইচ্ছা
    0.46
     ARRAY
    0.46
     மத்தியில்
    0.46
     hemodynamic
    0.46
    lingen
    0.46
     Иванович
    0.46
    Activations Density 0.000%

    No Known Activations