© 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. 127588
    Prev
    Next
    INDEX
    Explanations

    customers and browser

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

    extent, case, state

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ्व
    0.48
    过于
    0.48
    比如
    0.47
    🙉
    0.47
     वाटते
    0.47
    👎
    0.46
    는데
    0.46
    譬
    0.46
    èdent
    0.44
    เช่น
    0.44
    POSITIVE LOGITS
     hadn
    0.49
     unprecedented
    0.46
    contaminated
    0.44
     heated
    0.44
     distribut
    0.44
     volver
    0.42
     habían
    0.42
     duel
    0.42
     ruler
    0.42
     pozycji
    0.42
    Activations Density 0.001%

    No Known Activations