© 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. 57374
    Prev
    Next
    INDEX
    Explanations

    chemical formulas with elements and numbers

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

    chemical formulas and compounds containing transition metals and their numeric subscripts.

    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
     tools
    -0.77
     réfléchir
    -0.76
     Hans
    -0.75
     törté
    -0.75
     Times
    -0.75
    瑜伽
    -0.73
     Gesch
    -0.72
     bland
    -0.72
     значит
    -0.70
     hisz
    -0.70
    POSITIVE LOGITS
    ibig
    0.84
    imakasih
    0.84
    ೨
    0.83
     העולם
    0.81
    izient
    0.81
    boer
    0.81
    backend
    0.80
    formazione
    0.79
     backend
    0.77
    Ripple
    0.77
    Activations Density 0.039%

    No Known Activations