© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205180
    Prev
    Next
    INDEX
    Explanations

    Server Daemon, affiliated with

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

    find work or good outcomes

    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
    Negative Logits
    🚩
    0.42
    Connector
    0.40
    懵
    0.40
     useSelector
    0.40
    溝
    0.40
    direction
    0.39
     getUser
    0.39
    ll
    0.39
    nan
    0.39
     äh
    0.39
    POSITIVE LOGITS
     분석
    0.55
     اعلی
    0.50
    stacks
    0.47
     بسیاری
    0.46
    菽
    0.46
    следования
    0.46
     stacked
    0.45
    ாதி
    0.44
    쌉
    0.43
     विश्
    0.43
    Activations Density 0.000%

    No Known Activations