© 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. 24047
    Prev
    Next
    INDEX
    Explanations

    legal case names

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

    The neuron detects numeric tokens formatted as decimal numbers (i.e., numbers with a fractional “.x” part).

    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
    盉
    -3.34
    鼍
    -3.19
     unſ
    -2.86
    
    -2.86
     ſever
    -2.77
     miniaturka
    -2.75
    และ
    -2.73
    ⚌
    -2.70
     รวม
    -2.67
     quintessential
    -2.64
    POSITIVE LOGITS
    ↵↵
    2.92
    s
    2.83
    us
    2.77
    es
    2.70
     blatantly
    2.63
     relentlessly
    2.58
    …..
    2.52
     supremely
    2.48
     or
    2.47
    k
    2.45
    Activations Density 0.024%

    No Known Activations