© 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. 136326
    Prev
    Next
    INDEX
    Explanations

    corrugated, Ring, Lost, corrupt

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

    technology diversity

    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
    ruč
    0.50
    ጠና
    0.49
    ாண்டு
    0.46
     федера
    0.45
     ハンドバッグ
    0.44
    track
    0.43
    }=(\
    0.41
    Governance
    0.41
     актива
    0.41
    跡
    0.41
    POSITIVE LOGITS
     hedon
    0.54
     Referential
    0.53
     avant
    0.51
     neo
    0.50
    线性
    0.50
     positiv
    0.50
     Neo
    0.47
     absurd
    0.46
     poetic
    0.46
     lyric
    0.46
    Activations Density 0.001%

    No Known Activations