© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11856
    Prev
    Next
    INDEX
    Explanations

    layout and attributes

    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_7_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
     in
    1.83
    er
    1.78
     to
    1.77
     and
    1.75
    يج
    1.73
    .
    1.71
    ↵↵
    1.64
     throughout
    1.64
     have
    1.64
     mẽ
    1.60
    POSITIVE LOGITS
    μία
    2.17
    Попис
    2.11
    빡
    2.09
    Named
    2.05
    所谓的
    2.03
    vah
    2.03
     облі
    2.03
    愣
    1.98
    叫做
    1.98
    osk
    1.97
    Activations Density 0.047%

    No Known Activations