© 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. 10-GEMMASCOPE-RES-131K
    7. 130369
    Prev
    Next
    INDEX
    Explanations

    log formatting patterns

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

    This neuron responds to hyphen/minus characters (the “–” or “-” sign), especially when used as a numeric or chemical minus/exponent marker.

    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
    the
    -2.89
    垕
    -2.77
    ⮜
    -2.73
    </sup>
    -2.61
    书房
    -2.50
    塍
    -2.39
    ⟞
    -2.38
    s
    -2.33
    a
    -2.30
    </h4>
    -2.27
    POSITIVE LOGITS
     selben
    2.70
    鏐
    2.58
    䉴
    2.52
    
    2.39
    виси
    2.36
    
    2.31
    裥
    2.30
     größere
    2.28
    玊
    2.27
    朥
    2.19
    Activations Density 0.017%

    No Known Activations