© 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. 110808
    Prev
    Next
    INDEX
    Explanations

    speeches and announcements

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

    lists, specific names

    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
    이고
    0.50
    PY
    0.50
    的工作
    0.44
     Rows
    0.44
     rows
    0.44
    最具
    0.44
    的项目
    0.44
    쾰
    0.44
    尔
    0.43
    äude
    0.43
    POSITIVE LOGITS
     Connelly
    0.52
     Morr
    0.50
    ﹰ
    0.49
     बुजुर्ग
    0.49
     Konstant
    0.49
     समानता
    0.48
     Hobson
    0.48
     Gener
    0.48
     സ്ത്ര
    0.47
     قی
    0.47
    Activations Density 0.000%

    No Known Activations