© 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. 3132
    Prev
    Next
    INDEX
    Explanations

    capillary gas chromatography cellulose plates

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

    technical descriptions of laboratory equipment and chromatography columns.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric tokens and measurement values in technical method descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     leaf
    -0.77
     deaf
    -0.74
     سامسون
    -0.73
    砦
    -0.71
    ogni
    -0.70
    ҥ
    -0.69
     perfekte
    -0.69
     equivo
    -0.69
    onies
    -0.69
    Best
    -0.69
    POSITIVE LOGITS
    Luz
    0.81
     inš
    0.73
     handker
    0.68
     Bodega
    0.66
    盃
    0.65
    études
    0.64
    Tf
    0.63
     Zang
    0.63
    робнее
    0.62
    cens
    0.60
    Activations Density 0.077%

    No Known Activations