© 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. 224218
    Prev
    Next
    INDEX
    Explanations

    Frank Underwood, asbestos, or continue using

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

    units and descriptions

    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
    فهام
    0.52
    還是
    0.46
     comentario
    0.46
     Cambio
    0.46
    ।
    0.45
     گلو
    0.44
    وع
    0.44
     Werte
    0.44
     perspectivas
    0.43
     aprob
    0.42
    POSITIVE LOGITS
    Netflix
    0.55
    z
    0.50
    ’
    0.50
    K
    0.49
    vs
    0.48
    k
    0.48
    umoto
    0.48
    kom
    0.47
     mobilise
    0.46
    NIH
    0.46
    Activations Density 0.001%

    No Known Activations