© 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. 197984
    Prev
    Next
    INDEX
    Explanations

    news papers / health / attending

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

    incoming messages and general calls

    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
     pérd
    0.51
    -
    0.48
     pérdidas
    0.46
     auriculares
    0.46
     sombras
    0.46
     métal
    0.46
     complexes
    0.45
    <strong>
    0.45
     metas
    0.45
     middlemen
    0.45
    POSITIVE LOGITS
    titor
    0.50
    nych
    0.49
    crash
    0.48
    ERT
    0.47
    writer
    0.47
    individ
    0.47
    ADOC
    0.46
    oselect
    0.46
    setType
    0.46
    cfg
    0.46
    Activations Density 0.000%

    No Known Activations