© 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. 104547
    Prev
    Next
    INDEX
    Explanations

    specifying counts and ranges

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

    The neuron fires on numeric tokens and numeric sequences (i.e. digits, counts, version numbers, and other numerals).

    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
     Czę
    -0.96
    وكان
    -0.86
    깝
    -0.85
     होगा
    -0.82
     tphcm
    -0.79
    miami
    -0.78
     Quintet
    -0.77
    ibly
    -0.77
    wende
    -0.76
    reibt
    -0.76
    POSITIVE LOGITS
     all
    1.19
    全部
    1.10
     entirety
    1.04
     entire
    1.03
     весь
    0.98
    entire
    0.97
    整个
    0.92
    全体
    0.89
    Entire
    0.85
     все
    0.84
    Activations Density 0.102%

    No Known Activations