© 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. 22-GEMMASCOPE-RES-131K
    7. 25842
    Prev
    Next
    INDEX
    Explanations

    pistols and sport utility vehicles

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

    This neuron detects mentions of product-type nouns—especially vehicle (SUV, sport utility) and firearm (pistol) categories.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ндарт
    -2.31
    鉝
    -2.06
    ⟝
    -2.03
    臯
    -1.95
     mesmas
    -1.95
    瑨
    -1.90
    也没
    -1.88
     knows
    -1.83
    ֫
    -1.83
    herent
    -1.81
    POSITIVE LOGITS
    ка
    2.42
    .
    2.25
    '}
    2.00
    𓋼
    2.00
    ˂
    1.98
     могла
    1.91
    颁
    1.88
    たちは
    1.82
    ==>
    1.81
     плана
    1.79
    Activations Density 0.017%

    No Known Activations