© 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. 152811
    Prev
    Next
    INDEX
    Explanations

    wire, commas, separators

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

    concepts and their understanding

    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
    批評
    0.49
    uent
    0.47
    каз
    0.46
     Critics
    0.46
    cF
    0.45
    sau
    0.44
    Critics
    0.44
    irt
    0.43
    </h3>
    0.43
    auf
    0.42
    POSITIVE LOGITS
     overdraft
    0.57
    改めて
    0.56
    nais
    0.50
     오픈
    0.50
     overtake
    0.49
     dependences
    0.49
     पुन्हा
    0.48
     다시
    0.47
    मुख
    0.47
    프
    0.47
    Activations Density 0.001%

    No Known Activations