© 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. 145215
    Prev
    Next
    INDEX
    Explanations

    locationartsclientstartersdeath

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

    probability, model, estimates

    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
    ל
    0.66
    y
    0.55
    nder
    0.55
    ي
    0.55
    an
    0.54
     Pack
    0.52
    י
    0.52
     Чтобы
    0.51
    ar
    0.50
    Você
    0.50
    POSITIVE LOGITS
     notValid
    0.46
     kese
    0.44
     reassure
    0.44
     stalemate
    0.44
     fonctionnal
    0.44
    LevelLinking
    0.43
     antiseptic
    0.43
     ascorbic
    0.43
     quantitative
    0.42
     항
    0.42
    Activations Density 0.000%

    No Known Activations