© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 35007
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and properties

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

    symbols used in scientific or technical notation, particularly hyphens in scientific papers and code documentation.

    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
     String
    -0.85
     Ath
    -0.76
     Async
    -0.75
    olini
    -0.71
     Nö
    -0.69
     Zwischen
    -0.68
    stino
    -0.67
     Arch
    -0.67
    Cassandra
    -0.66
     lö
    -0.66
    POSITIVE LOGITS
    egl
    0.69
    abras
    0.65
    Про
    0.64
    lojes
    0.63
    icz
    0.62
    tiera
    0.62
    堅持
    0.61
     droite
    0.61
     episodios
    0.61
    pai
    0.60
    Activations Density 0.071%

    No Known Activations