© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1842
    Prev
    Next
    INDEX
    Explanations

    new distinct cultivar or variety

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

    legal and technical document citations, particularly patent and class numbers.

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

    This neuron consistently lights up on long sequences of digits or alphanumeric codes (e.g. patent numbers or classification codes).

    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
     कह
    -0.77
    municipi
    -0.76
     occupied
    -0.76
    StateList
    -0.72
    luas
    -0.72
     henceforth
    -0.71
    払い
    -0.69
    arischen
    -0.69
    смотре
    -0.69
    olio
    -0.68
    POSITIVE LOGITS
    DIG
    1.44
     DIG
    1.17
    dig
    1.05
     Dig
    1.00
    Dig
    0.94
    ppig
    0.92
     dig
    0.92
     DIGEST
    0.91
     torna
    0.90
     digger
    0.89
    Activations Density 0.075%

    No Known Activations