© 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. 130942
    Prev
    Next
    INDEX
    Explanations

    checking for specific following tokens

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

    long response

    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
     Portfolio
    0.51
     Builders
    0.50
    Craft
    0.49
    /
    0.48
    <b>
    0.47
    ts
    0.47
    apost
    0.47
    $,
    0.46
     Code
    0.46
     builders
    0.46
    POSITIVE LOGITS
     messageShow
    0.55
    водитель
    0.55
     источник
    0.50
     окно
    0.49
    翳
    0.48
     источники
    0.48
     полное
    0.47
    linkOpacity
    0.46
    τή
    0.46
    ExternalTaskPojo
    0.46
    Activations Density 0.000%

    No Known Activations