© 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. 190508
    Prev
    Next
    INDEX
    Explanations

    Supreme Court cases

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

    technical terms and descriptions

    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
     мали
    0.47
    enzione
    0.47
     Macht
    0.45
    czki
    0.45
    '">
    0.45
     проверки
    0.45
     Índice
    0.45
    া
    0.45
     причине
    0.45
     blazer
    0.44
    POSITIVE LOGITS
    وده
    0.47
     to
    0.46
    atele
    0.44
    s
    0.43
    until
    0.43
     throughout
    0.42
    Genome
    0.42
    ppa
    0.41
     stif
    0.41
    पोज
    0.41
    Activations Density 0.000%

    No Known Activations