© 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. 80148
    Prev
    Next
    INDEX
    Explanations

    Jesus Christ, collapsed onto, protects words

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

    ways of responding

    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
    毕业生
    0.45
     conexiones
    0.43
     сделали
    0.43
    zeuge
    0.43
     nameWithOwner
    0.43
     изго
    0.42
     кү
    0.42
    埌
    0.42
     подготов
    0.42
    ӗ
    0.41
    POSITIVE LOGITS
    s
    0.72
    as
    0.65
    at
    0.63
    a
    0.61
    t
    0.55
    ad
    0.55
    ar
    0.54
    et
    0.54
    o
    0.52
    ু
    0.52
    Activations Density 0.000%

    No Known Activations