© 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. 34-GEMMASCOPE-RES-131K
    4. 60314
    Prev
    Next
    INDEX
    Explanations

    betting markets and odds

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

    The neuron strongly activates on non-word tokens—especially punctuation marks (like ‘!’, ‘?’, apostrophes), standalone digits, and other symbols—i.e. emphasis/​symbol characters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    techniques
    -0.77
    throm
    -0.77
    soever
    -0.77
    skyline
    -0.76
     nije
    -0.76
    liberal
    -0.75
    NEET
    -0.75
    Outbound
    -0.74
     cabello
    -0.74
     Tú
    -0.74
    POSITIVE LOGITS
     betting
    1.13
     value
    1.09
     bet
    1.07
     fade
    1.06
    Fade
    0.99
     Fade
    0.98
    value
    0.97
     fading
    0.93
     markets
    0.91
    fade
    0.91
    Activations Density 0.006%

    No Known Activations