© 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. 176872
    Prev
    Next
    INDEX
    Explanations

    unless the, Black HP

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

    important questions and considerations

    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
    ﮐ
    0.46
     ಸಿ
    0.46
     GRANT
    0.46
    ITTLE
    0.45
    的选择
    0.44
    ISTRATION
    0.44
    苇
    0.44
    PREFIX
    0.43
     PAST
    0.43
    잿
    0.43
    POSITIVE LOGITS
    texto
    0.50
     certificados
    0.47
    tras
    0.46
    jing
    0.46
    menu
    0.45
     पैन
    0.45
    ordnet
    0.45
    iau
    0.45
     certificado
    0.45
    zzo
    0.44
    Activations Density 0.000%

    No Known Activations