© 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. 122107
    Prev
    Next
    INDEX
    Explanations

    record everything

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

    strategic audience keywords decisions

    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
    𝚙
    0.53
    ést
    0.52
     souvent
    0.52
    trop
    0.51
    timeouts
    0.50
     compagnies
    0.49
     corriente
    0.49
    vely
    0.48
     termites
    0.48
    strategy
    0.48
    POSITIVE LOGITS
     моно
    0.48
    。"
    0.46
    拖
    0.46
    。）
    0.44
     Disaster
    0.43
     ।
    0.43
    ）、
    0.43
     зака
    0.42
    枝
    0.42
     Eisen
    0.42
    Activations Density 0.000%

    No Known Activations