© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4712
    Prev
    Next
    INDEX
    Explanations

    sunscreen, hat, sunglasses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     ý
    1.25
    ->
    1.25
    Al
    1.18
    Fast
    1.17
     Yong
    1.17
    Para
    1.14
    약
    1.13
    W
    1.12
    Y
    1.12
    N
    1.11
    POSITIVE LOGITS
    phalodes
    2.04
    agangan
    2.03
    drawiam
    2.01
    quisites
    2.00
    unication
    1.96
    eszcze
    1.95
    予め
    1.94
    esine
    1.92
    reciate
    1.92
     regretted
    1.92
    Activations Density 0.002%

    No Known Activations