© 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. 128406
    Prev
    Next
    INDEX
    Explanations

    following certain punctuation

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

    regarding modifications, claim this, minor illness, responsibility around, list of, maintenance level, spirit forged

    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
     Bhagava
    0.52
     아이
    0.47
     chuẩn
    0.46
     ControllerBase
    0.46
     Dünya
    0.45
     khẩu
    0.45
    }!
    0.45
     vantaggio
    0.44
     口
    0.44
    可在
    0.44
    POSITIVE LOGITS
    Merr
    0.48
    רה
    0.44
    ലാണ്
    0.44
    DELAY
    0.44
    文件的
    0.43
    Tomorrow
    0.43
    Nomin
    0.42
    옆
    0.42
    곁
    0.42
    ლე
    0.42
    Activations Density 0.001%

    No Known Activations