© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31516
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    carn
    -0.72
    aar
    -0.72
    らん
    -0.68
     SK
    -0.67
    sac
    -0.67
     ruler
    -0.66
    decrypted
    -0.64
    unwrap
    -0.63
    !".
    -0.63
    婚礼
    -0.63
    POSITIVE LOGITS
    Contributor
    0.65
    IRI
    0.65
    onnage
    0.64
    getDocument
    0.64
     مناف
    0.63
    傳
    0.63
    minHeight
    0.62
     ки
    0.62
    Delegate
    0.61
    HB
    0.60
    Activations Density 0.079%

    No Known Activations