© 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. 91957
    Prev
    Next
    INDEX
    Explanations

    plant suppliers

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

    numeric values and code-related elements like copyright notices and technical specifications.

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

    The neuron is primarily activated by standalone numeric tokens (numbers and digits) in the text.

    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
    initial
    -0.73
    yo
    -0.67
     berhubungan
    -0.66
     nehmen
    -0.66
     TOTAL
    -0.65
    opening
    -0.65
     apoy
    -0.65
    Dropbox
    -0.65
    filling
    -0.65
    INITIAL
    -0.65
    POSITIVE LOGITS
    chiat
    0.74
    QueryResult
    0.73
     landslide
    0.73
    kyt
    0.70
    inputStream
    0.69
     clips
    0.68
     liability
    0.66
    Tatiana
    0.65
    REQUIRES
    0.64
    unday
    0.63
    Activations Density 0.076%

    No Known Activations