© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11490
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron specializes in spotting numeric tokens and numeric expressions (digits, hyphens, and related punctuation in measurements, model numbers, or ranges).

    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
     gewi
    -1.63
     hébergement
    -1.63
     équipement
    -1.59
     emballage
    -1.59
     escalier
    -1.58
     hemd
    -1.54
     jezt
    -1.46
    emballage
    -1.42
     étages
    -1.42
     Hauses
    -1.41
    POSITIVE LOGITS
     is
    1.68
     was
    1.58
    ၠ
    1.47
     four
    1.46
     seemed
    1.38
     .....
    1.38
    When
    1.38
     When
    1.35
     considerable
    1.34
     h
    1.34
    Activations Density 0.237%

    No Known Activations