© 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. 108210
    Prev
    Next
    INDEX
    Explanations

    presents reports or recommendations

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

    indicate how or roughly how

    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
    퀵
    0.39
    잤
    0.39
     Dat
    0.38
     decom
    0.38
     পাকিস্তানিদের
    0.38
    DataType
    0.37
    modelLogin
    0.37
     Builds
    0.36
    ProductId
    0.36
    Line
    0.36
    POSITIVE LOGITS
    RENCE
    0.56
    มิ
    0.50
     SMITH
    0.47
    倶
    0.46
    楹
    0.46
    都
    0.45
     bourse
    0.44
    近年
    0.44
    AGUE
    0.44
    financed
    0.44
    Activations Density 0.001%

    No Known Activations