© 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. 191405
    Prev
    Next
    INDEX
    Explanations

    mobile apps or computer programs

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

    AI conversations and 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
    ブ
    0.55
    伈
    0.53
    тись
    0.53
    ються
    0.52
    で行
    0.52
    цени
    0.51
    ニ
    0.49
    шт
    0.49
    ユニ
    0.49
    е
    0.49
    POSITIVE LOGITS
    ou
    0.56
    ever
    0.52
    aid
    0.50
    ight
    0.49
    dard
    0.46
    uid
    0.46
    oules
    0.46
    loed
    0.46
    bathy
    0.46
    kit
    0.45
    Activations Density 0.000%

    No Known Activations