© 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. 115909
    Prev
    Next
    INDEX
    Explanations

    competitive shooting speed

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

    The neuron fires strongly on numeric tokens and alphanumeric model/designation strings (e.g. measurements, calibers, and gun model numbers).

    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
     princesses
    -0.84
    cia
    -0.75
    HR
    -0.74
     HR
    -0.74
     McLean
    -0.73
     vật
    -0.72
    cleo
    -0.70
    Strawberry
    -0.69
     HYDRO
    -0.69
    sptr
    -0.69
    POSITIVE LOGITS
    Steel
    0.95
     IP
    0.92
     Steel
    0.89
     STEEL
    0.87
    ips
    0.86
     competition
    0.85
     fastest
    0.82
    IP
    0.81
     speed
    0.80
     tốc
    0.77
    Activations Density 0.028%

    No Known Activations