© 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. 79118
    Prev
    Next
    INDEX
    Explanations

    metallicity and elements

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

    academic and scientific document formatting elements, particularly author names and metadata.

    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
     Fuse
    -0.91
     Compounds
    -0.82
     goblet
    -0.77
    明的
    -0.74
    無限
    -0.73
     verdicts
    -0.73
    spitze
    -0.70
     fillets
    -0.70
     doughnut
    -0.70
    scored
    -0.69
    POSITIVE LOGITS
     iron
    0.98
     Iron
    0.87
    bable
    0.85
    Iron
    0.84
    oup
    0.82
     Sauerstoff
    0.80
    Protein
    0.77
     abundance
    0.76
    pstmt
    0.74
    deemed
    0.70
    Activations Density 0.038%

    No Known Activations