© 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. 175406
    Prev
    Next
    INDEX
    Explanations

    locations and activities

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

    code, programming, mathematics

    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
     periód
    0.48
     spécifique
    0.45
    iseries
    0.44
     श्रृंखला
    0.43
     específicos
    0.43
    த்தோ
    0.42
     específica
    0.42
    ֮
    0.42
     ट्व
    0.42
    товых
    0.42
    POSITIVE LOGITS
    ’
    0.52
    e
    0.49
    nson
    0.49
     ~(
    0.49
    Americans
    0.47
    t
    0.47
    mong
    0.47
    acquisition
    0.47
    語言
    0.46
    -‘
    0.46
    Activations Density 0.000%

    No Known Activations