© 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. 113379
    Prev
    Next
    INDEX
    Explanations

    restrictions, beating, described, Georgia, claims

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

    for shipping

    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
    ву
    0.53
    ću
    0.53
    ಕರ್
    0.50
    वेलकम
    0.50
    ೮
    0.49
    к
    0.48
    лье
    0.47
    >',
    0.47
    тельный
    0.46
    д
    0.46
    POSITIVE LOGITS
     KILL
    0.45
     Racing
    0.44
     Shooting
    0.44
    atoria
    0.44
     Ranked
    0.43
     FIFA
    0.43
     Moving
    0.43
    ON
    0.42
     But
    0.42
     Getting
    0.42
    Activations Density 0.002%

    No Known Activations