© 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. 54122
    Prev
    Next
    INDEX
    Explanations

    brand mentions

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

    likes cats and dogs

    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
    怜
    0.55
    𝗆
    0.49
    第二个
    0.47
    裵
    0.47
    婄
    0.46
    نڈ
    0.46
     Cheyenne
    0.46
    मित्र
    0.45
    鄧
    0.45
     प्लस
    0.45
    POSITIVE LOGITS
    o
    0.50
    u
    0.50
    urun
    0.50
    a
    0.50
    e
    0.49
    le
    0.49
    ut
    0.48
    elekt
    0.48
    OL
    0.48
    antara
    0.48
    Activations Density 0.000%

    No Known Activations