© 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. 180168
    Prev
    Next
    INDEX
    Explanations

    production batch

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

    neutral or unchanged

    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
    沺
    0.48
    平时
    0.44
     Estas
    0.42
     %\
    0.42
    如
    0.41
    如图
    0.41
     exemples
    0.40
    亲
    0.40
     exemple
    0.39
     treinamento
    0.39
    POSITIVE LOGITS
    ess
    0.49
    uxi
    0.49
     beer
    0.49
    ysm
    0.48
    UTICAL
    0.47
     dearly
    0.46
     kuning
    0.46
     いっ
    0.46
     turquoise
    0.46
    となった
    0.46
    Activations Density 0.000%

    No Known Activations