© 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. 10-GEMMASCOPE-RES-131K
    7. 14357
    Prev
    Next
    INDEX
    Explanations

    command execution

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

    The neuron flags occurrences of the identifier “cmd” (as in code examples referring to a command variable or call).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -3.05
    ઁ
    -2.78
    砹
    -2.73
    }
    -2.70
     That
    -2.63
     They
    -2.52
    ୌ
    -2.47
    endront
    -2.45
    </h3>
    -2.44
     ‘‘
    -2.44
    POSITIVE LOGITS
    筇
    2.84
            
    2.72
    1
    2.66
    y
    2.61
    \
    2.56
     preguntar
    2.55
    -
    2.53
    ができます
    2.52
     soo
    2.50
     refroid
    2.50
    Activations Density 0.002%

    No Known Activations