© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12082
    Prev
    Next
    INDEX
    Explanations

    names followed by speech or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    斕
    1.86
    (__('
    1.78
     giới
    1.75
    ⁄
    1.66
    ES
    1.64
    දහ
    1.63
    Hình
    1.61
    Με
    1.60
    Ps
    1.58
    headed
    1.55
    POSITIVE LOGITS
    رین
    2.13
    н
    2.05
    oer
    1.99
    ر
    1.95
    r
    1.93
    rul
    1.92
    ва
    1.88
    د
    1.86
     administ
    1.85
    ו
    1.85
    Activations Density 0.001%

    No Known Activations