© 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. 10-GEMMASCOPE-RES-131K
    7. 102895
    Prev
    Next
    INDEX
    Explanations

    names and associated titles

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

    This neuron responds to tokens that combine letters with digits (i.e. alphanumeric strings with attached numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    但
    -3.38
    f
    -2.89
    也
    -2.88
    E
    -2.86
    要
    -2.80
     But
    -2.78
    但是
    -2.69
     اما
    -2.64
    THE
    -2.61
    就
    -2.59
    POSITIVE LOGITS
     vorige
    2.95
    赑
    2.91
    𓋼
    2.84
    ᛬
    2.80
    𞤢
    2.75
    鹛
    2.69
    狴
    2.69
    ludes
    2.67
    |"
    2.63
     ARNOLD
    2.63
    Activations Density 0.058%

    No Known Activations