© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108201
    Prev
    Next
    INDEX
    Explanations

    medical condition statistics

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

    special characters and symbols used in programming and documentation formatting.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     trot
    -0.72
    Джерела
    -0.68
     Patricia
    -0.67
     contagion
    -0.64
     demar
    -0.63
     retribution
    -0.62
     chas
    -0.61
     grandeur
    -0.61
     thrombosis
    -0.61
    updatedAt
    -0.60
    POSITIVE LOGITS
    twenty
    0.93
    many
    0.89
     TWENTY
    0.86
    cismo
    0.81
     Pian
    0.77
     Twenty
    0.75
    rageous
    0.75
    membered
    0.72
    minster
    0.72
     дам
    0.72
    Activations Density 0.367%

    No Known Activations