© 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. 50813
    Prev
    Next
    INDEX
    Explanations

    work towards

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

    Cartesian coordinates, audience, lives, hooked

    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
     os
    0.46
     aut
    0.45
     enca
    0.45
     T
    0.45
     baixar
    0.45
     lil
    0.44
     General
    0.44
    新疆
    0.44
     Cantonese
    0.43
     Ukraj
    0.43
    POSITIVE LOGITS
    ۴
    0.48
     அடைய
    0.46
    ज्ज
    0.46
    ździe
    0.45
    ༡
    0.45
    }",
    0.44
    ५
    0.44
    –
    0.44
    \":
    0.44
    retail
    0.44
    Activations Density 0.000%

    No Known Activations