© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 74983
    Prev
    Next
    INDEX
    Explanations

    california abbreviations

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

    The neuron detects numeric tokens (digits and number sequences), especially those appearing in citations and reference entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     etab
    -0.89
    胶
    -0.81
     mereka
    -0.79
    قلاب
    -0.79
    onto
    -0.79
     paiement
    -0.78
     agreg
    -0.77
    urllib
    -0.76
    тнес
    -0.75
    ishing
    -0.74
    POSITIVE LOGITS
     Conjug
    0.88
     will
    0.85
    érias
    0.85
     Silvio
    0.82
    appan
    0.81
    ṳ
    0.80
    ubakar
    0.79
    ेशन
    0.79
    kozá
    0.79
    mės
    0.78
    Activations Density 0.001%

    No Known Activations