© 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. 228615
    Prev
    Next
    INDEX
    Explanations

    voting on

    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
    =>
    0.50
    and
    0.49
    habitude
    0.48
    niveau
    0.47
    slf
    0.46
    şi
    0.45
    kelly
    0.45
    লাইন
    0.44
    ină
    0.44
    m
    0.44
    POSITIVE LOGITS
     ज़रूरत
    0.48
     eateries
    0.44
     villas
    0.44
     צריך
    0.44
    มีการ
    0.42
    ዊ
    0.42
     calculators
    0.42
     affluent
    0.41
     interpolated
    0.41
     distributions
    0.41
    Activations Density 0.000%

    No Known Activations