© 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. 34-GEMMASCOPE-RES-131K
    7. 103082
    Prev
    Next
    INDEX
    Explanations

    ranged attack

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

    This neuron detects numeric and game‐rule stat tokens—especially dice expressions and numeric values—in RPG rule texts.

    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
     امنیت
    -0.67
    প্র
    -0.67
    ITHUB
    -0.66
    aix
    -0.66
    Durham
    -0.66
    Sic
    -0.65
    🟨
    -0.65
     дефек
    -0.65
    海岸
    -0.64
     lietu
    -0.64
    POSITIVE LOGITS
     électriques
    0.96
    兴奋
    0.79
    bish
    0.79
    ESS
    0.79
     resale
    0.77
    ifi
    0.75
    Ւ
    0.74
    uwa
    0.73
     bypassed
    0.71
     alcanzado
    0.70
    Activations Density 0.011%

    No Known Activations