© 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. 103174
    Prev
    Next
    INDEX
    Explanations

    guns and shooting

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

    The neuron is primarily detecting numeric tokens (sequences of digits) such as calibers, model numbers, measurements, and other purely numeric values.

    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
     arrancar
    -1.06
     السلطة
    -1.02
    🫓
    -0.90
    ждены
    -0.88
    inals
    -0.86
    mą
    -0.85
    щики
    -0.85
    glyph
    -0.84
    DEFINITIONS
    -0.82
     Alemania
    -0.82
    POSITIVE LOGITS
     gun
    1.62
     firearm
    1.57
     firearms
    1.53
     shooters
    1.50
     recoil
    1.44
     muzzle
    1.40
     rifle
    1.38
     Ruger
    1.38
     shooting
    1.35
     Glock
    1.35
    Activations Density 0.117%

    No Known Activations