© 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. 168452
    Prev
    Next
    INDEX
    Explanations

    list item or other people

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

    comparative or superlative states

    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
     http
    0.55
     také
    0.50
     Produk
    0.50
     Direkt
    0.50
     utilisées
    0.49
     *\
    0.49
     aras
    0.49
     svijet
    0.49
     étudier
    0.48
    自然的
    0.48
    POSITIVE LOGITS
    t
    0.49
    on
    0.49
    gens
    0.47
    y
    0.46
    ped
    0.46
    s
    0.44
    gend
    0.44
    ly
    0.43
    idos
    0.43
    othe
    0.43
    Activations Density 0.000%

    No Known Activations