© 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. 139141
    Prev
    Next
    INDEX
    Explanations

    packaging or retail packaging

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

    why reset

    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
     controlar
    0.52
     contactos
    0.50
    所有
    0.49
     llevar
    0.49
    閘
    0.48
    lgende
    0.48
     decisões
    0.48
    行政
    0.48
     gestionar
    0.48
     instalaciones
    0.47
    POSITIVE LOGITS
    ंझ
    0.48
     nifty
    0.46
     Basket
    0.45
     Stable
    0.45
     whats
    0.44
     Whats
    0.44
     basket
    0.44
    ेश्व
    0.44
     Tolstoy
    0.44
    <unused12>
    0.43
    Activations Density 0.000%

    No Known Activations