© 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. 71252
    Prev
    Next
    INDEX
    Explanations

    official site

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

    possible worlds, virtual worlds

    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
    <unused657>
    0.57
     vucc
    0.55
     samano
    0.55
     બનાવે
    0.53
    <unused235>
    0.52
     Ива
    0.51
    ழிய
    0.51
     використову
    0.50
     Maximilian
    0.50
    <unused471>
    0.49
    POSITIVE LOGITS
     rider
    0.50
    runner
    0.47
     cyber
    0.46
    supplier
    0.45
    stmt
    0.45
    ing
    0.44
     world
    0.44
     fill
    0.42
     hallar
    0.42
     part
    0.42
    Activations Density 0.000%

    No Known Activations