© 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. 28888
    Prev
    Next
    INDEX
    Explanations

    who is, doing evil

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

    list markers and punctuation

    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
     或者
    0.49
    count
    0.43
    ya
    0.43
    icia
    0.43
    content
    0.43
    看
    0.41
    或者
    0.40
    g
    0.40
    agg
    0.40
     如果
    0.40
    POSITIVE LOGITS
     closer
    0.49
     deviennent
    0.49
     maximising
    0.47
     pleinement
    0.46
     lawns
    0.46
     teknologi
    0.46
     températures
    0.45
     recharging
    0.45
     nesses
    0.45
     sawing
    0.45
    Activations Density 0.000%

    No Known Activations