© 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. 166671
    Prev
    Next
    INDEX
    Explanations

    professional services and owners

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

    brackets, cause, logs, leads, trace

    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
    粡
    0.53
    pretrained
    0.48
    嶠
    0.44
    ='".$
    0.44
    ｸ
    0.43
    ಾರ
    0.43
    alamy
    0.43
    ナトリウム
    0.43
    \%)
    0.42
    stateMutability
    0.42
    POSITIVE LOGITS
     Vá
    0.54
     diá
    0.54
     appar
    0.52
     civ
    0.51
     ín
    0.51
     ñ
    0.49
     CEOs
    0.49
     deliber
    0.48
     dív
    0.48
     livres
    0.48
    Activations Density 0.000%

    No Known Activations