© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16145
    Prev
    Next
    INDEX
    Explanations

    group or, while he, members are

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

    think you

    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
     দেয়
    0.52
     פ
    0.47
    ários
    0.47
    ни
    0.47
    alahan
    0.47
    Avro
    0.46
     দল
    0.46
     noter
    0.46
    ando
    0.44
     Univer
    0.44
    POSITIVE LOGITS
     cláus
    0.52
    ビッグ
    0.50
     Cout
    0.44
    👏👏👏👏
    0.44
    න්ධ
    0.44
     inexplicable
    0.43
     claust
    0.43
     tronc
    0.42
     viciss
    0.42
     reinado
    0.42
    Activations Density 0.000%

    No Known Activations