© 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. 194656
    Prev
    Next
    INDEX
    Explanations

    responsibility for packages

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

    names and places

    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
    tral
    0.52
    ell
    0.51
    ADO
    0.51
    sl
    0.48
    不僅
    0.48
    </strong>
    0.48
    %\
    0.48
    ado
    0.47
    lio
    0.46
    alog
    0.46
    POSITIVE LOGITS
    जेदार
    0.46
     ठाकरे
    0.46
     Hrvatske
    0.45
     disponibilités
    0.44
    дик
    0.43
     Eucalyptus
    0.43
     саны
    0.43
    콜
    0.43
    ނ
    0.43
     carbides
    0.42
    Activations Density 0.000%

    No Known Activations