© 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. 22-GEMMASCOPE-RES-131K
    7. 128856
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on standalone numeric tokens—particularly digits in lists or sequences (e.g. terms of a series, array values, or fractions) rather than ordinary words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     beve
    -0.91
     resina
    -0.90
    她们
    -0.90
     quarta
    -0.89
     nube
    -0.89
     vekt
    -0.88
     indeks
    -0.88
     Primaria
    -0.87
     asseg
    -0.87
     domicili
    -0.86
    POSITIVE LOGITS
     Candidates
    0.92
    htbp
    0.91
     or
    0.91
    حتی
    0.89
    toDouble
    0.89
     genitalia
    0.86
     one
    0.85
     civil
    0.84
     candidates
    0.81
    cella
    0.81
    Activations Density 0.028%

    No Known Activations