© 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. 130994
    Prev
    Next
    INDEX
    Explanations

    when certain

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

    genuine laughter

    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
    tissue
    0.47
    cel
    0.46
    trained
    0.43
    goal
    0.43
    treated
    0.43
     జన్
    0.43
    UL
    0.42
    s
    0.42
     hok
    0.42
    goals
    0.41
    POSITIVE LOGITS
    建议
    0.52
    ড্ডা
    0.47
    葶
    0.47
    某些
    0.46
    讓
    0.45
    ყენ
    0.44
    setForeground
    0.43
    定价
    0.43
    酺
    0.43
    改變
    0.43
    Activations Density 0.001%

    No Known Activations