© 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. 54161
    Prev
    Next
    INDEX
    Explanations

    shooting at sport events

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

    The neuron fires strongly on numeric tokens—especially measurements like “10”, “25”, “50” and the unit “metre” in shooting‐event descriptions.

    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
    chkin
    -0.78
     فوتبال
    -0.76
     zemi
    -0.73
    plasma
    -0.72
     halı
    -0.71
    🎾
    -0.71
    setNome
    -0.71
    fieldId
    -0.69
    бя
    -0.69
    찐
    -0.68
    POSITIVE LOGITS
     shooting
    1.51
     rifle
    1.34
     shoot
    1.27
     pistol
    1.25
    Shooting
    1.22
     Shooting
    1.17
    ISS
    1.17
     gun
    1.16
     Rifle
    1.16
     shoots
    1.15
    Activations Density 0.020%

    No Known Activations