© 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. 226373
    Prev
    Next
    INDEX
    Explanations

    distances or iOS simulator

    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
    кр
    0.48
    у
    0.48
    }^{+}=
    0.45
    ját
    0.45
    hect
    0.44
    heh
    0.44
     Ն
    0.44
    тре
    0.43
    ходя
    0.43
    лд
    0.43
    POSITIVE LOGITS
     Spread
    0.48
     Salute
    0.46
    鲜
    0.46
    دخل
    0.46
     Combin
    0.43
     Declare
    0.43
    Colour
    0.43
     Calor
    0.43
     Lets
    0.42
     setColor
    0.42
    Activations Density 0.000%

    No Known Activations