© 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. 212871
    Prev
    Next
    INDEX
    Explanations

    found more

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

    security warnings

    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
     contrôler
    0.53
     monarchy
    0.52
     agregar
    0.51
     trasferimento
    0.51
    ␶
    0.51
     aparato
    0.51
     timeCounter
    0.51
     chercher
    0.50
     identificar
    0.50
     manipulating
    0.50
    POSITIVE LOGITS
    h
    0.65
    il
    0.64
    e
    0.63
    in
    0.59
    u
    0.59
    an
    0.57
    a
    0.56
    i
    0.56
    er
    0.54
    da
    0.53
    Activations Density 0.000%

    No Known Activations