© 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. 38634
    Prev
    Next
    INDEX
    Explanations

    molar mass and ratio

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

    The neuron activates for the word "molar" in scientific and technical contexts, particularly in chemistry-related texts.

    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
     Grie
    -0.88
    レット
    -0.71
     Persön
    -0.69
    Pedro
    -0.69
     adresu
    -0.68
     STUD
    -0.67
    uoti
    -0.66
     Intestinal
    -0.66
    usehen
    -0.66
     Besuch
    -0.66
    POSITIVE LOGITS
    «
    0.79
     .=
    0.69
    եր
    0.66
    ModuleName
    0.64
    unl
    0.63
     Impf
    0.63
     массы
    0.63
    TokenNameLBRACE
    0.63
     reci
    0.62
    Brom
    0.62
    Activations Density 0.087%

    No Known Activations