© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67175
    Prev
    Next
    INDEX
    Explanations

    chance to win or survive

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

    The neuron activates on words that express likelihood or probability (e.g., chance, shot, hope, odds).

    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
    諼
    -1.90
    蜑
    -1.86
    鸱
    -1.80
    禤
    -1.79
     prendas
    -1.79
    ㆆ
    -1.78
     these
    -1.77
    珝
    -1.74
    ?”
    -1.73
     propietarios
    -1.72
    POSITIVE LOGITS
     of
    1.73
    —
    1.57
    ).
    1.41
    ue
    1.38
     /
    1.36
    h
    1.36
    s
    1.35
    x
    1.32
    [
    1.29
     chance
    1.27
    Activations Density 0.012%

    No Known Activations