© 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. 6533
    Prev
    Next
    INDEX
    Explanations

    official repositories

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

    categories or domains

    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
    awaited
    0.60
    p
    0.52
    larla
    0.50
    cor
    0.49
     convid
    0.49
    complete
    0.49
    lives
    0.48
    umma
    0.48
    id
    0.48
    ol
    0.48
    POSITIVE LOGITS
     Descriptive
    0.52
    ತ್
    0.49
    ృష్టి
    0.47
     shafts
    0.46
     isometry
    0.46
     Radiant
    0.45
    玤
    0.45
     Stonehenge
    0.45
     trajectories
    0.44
     skewers
    0.44
    Activations Density 0.000%

    No Known Activations