© 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. 220946
    Prev
    Next
    INDEX
    Explanations

    geography and phenology projects

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

    financial considerations

    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
     कार्याल
    0.52
     odometer
    0.52
     お
    0.50
     enzymatic
    0.50
     automata
    0.50
     ハンド
    0.48
     mediates
    0.47
     angiogenesis
    0.47
     cafes
    0.45
     encapsulates
    0.45
    POSITIVE LOGITS
    р
    0.47
    ва
    0.46
    cout
    0.46
    ικών
    0.46
    R
    0.46
    U
    0.43
     fréquente
    0.42
    va
    0.42
    既
    0.42
    h
    0.42
    Activations Density 0.001%

    No Known Activations