© 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. 13685
    Prev
    Next
    INDEX
    Explanations

    products and versions

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

    specific technologies and versions

    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
     upang
    0.54
    <unused99>
    0.51
     condemning
    0.49
    ূল্য
    0.47
     číslo
    0.47
     ശക്ത
    0.46
     iniciando
    0.46
    ടൊപ്പം
    0.46
    <unused1085>
    0.46
    ›
    0.45
    POSITIVE LOGITS
     models
    0.68
     versions
    0.64
     U
    0.59
    0.56
     designs
    0.55
     M
    0.55
     products
    0.55
    4
    0.53
     offerings
    0.53
     distributions
    0.52
    Activations Density 0.057%

    No Known Activations