© 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. 95032
    Prev
    Next
    INDEX
    Explanations

    words like required, turn, included, chain, mile

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

    simply cannot

    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
     quan
    0.49
     variances
    0.47
     coins
    0.46
     occasional
    0.46
     herbicides
    0.46
     pandas
    0.45
     occasionally
    0.45
    ’
    0.45
    中に
    0.44
     періо
    0.44
    POSITIVE LOGITS
    Entering
    0.50
    Введите
    0.47
    सलमान
    0.46
    Input
    0.44
    fält
    0.44
    është
    0.43
    alore
    0.43
    guin
    0.43
    ışt
    0.42
    usti
    0.42
    Activations Density 0.000%

    No Known Activations