© 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. 71183
    Prev
    Next
    INDEX
    Explanations

    criteria parameters

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

    file or online courses

    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
    _
    0.53
    ati
    0.52
    era
    0.51
    assa
    0.51
    ada
    0.50
    tenant
    0.50
    ura
    0.50
    fe
    0.49
    asa
    0.48
    osome
    0.48
    POSITIVE LOGITS
     critérios
    0.57
    스
    0.55
     cuál
    0.53
     quarrels
    0.53
     cuándo
    0.52
     parámetros
    0.51
     prejudicial
    0.51
    確か
    0.50
     신경
    0.50
     divine
    0.49
    Activations Density 0.000%

    No Known Activations