© 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. 29645
    Prev
    Next
    INDEX
    Explanations

    An increasedunique loveWatch rumorsoul at worktables with

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

    recognize, always, saw, pursuing, often

    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
    █
    0.51
     аўтаматы
    0.51
     техника
    0.50
    h
    0.49
     Australia
    0.49
     мощ
    0.49
     otomatis
    0.49
     techniques
    0.49
     Sally
    0.49
    แสง
    0.48
    POSITIVE LOGITS
    唯
    0.47
    izou
    0.46
    市
    0.46
    心
    0.45
    边
    0.45
    札
    0.45
    西
    0.44
    包
    0.44
    瓜
    0.43
    厄
    0.43
    Activations Density 0.000%

    No Known Activations