© 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. 43503
    Prev
    Next
    INDEX
    Explanations

    identifier values

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

    The neuron primarily detects numeric literals (numbers) embedded in code or text.

    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
    <i>
    -3.36
    an
    -3.02
    y
    -3.00
    This
    -2.80
    U
    -2.72
    a
    -2.70
    ︲
    -2.69
    </td>
    -2.66
    <em>
    -2.64
    al
    -2.64
    POSITIVE LOGITS
    葑
    2.56
     projektu
    2.55
     หรือ
    2.50
    爆笑
    2.45
     perfekte
    2.45
     leyendo
    2.45
    Инг
    2.42
    
    2.42
     sebagai
    2.41
    ῞
    2.41
    Activations Density 0.047%

    No Known Activations