© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74558
    Prev
    Next
    INDEX
    Explanations

    computer drivers

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

    The neuron activates on numeric identifiers (digits) that immediately follow “Driver” in code.

    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
    a
    -3.34
     .
    -3.13
    ."
    -3.02
    }
    -2.92
     '
    -2.92
    ]
    -2.83
    “
    -2.81
    4
    -2.78
    2
    -2.77
    </h4>
    -2.72
    POSITIVE LOGITS
    
    2.97
    狆
    2.95
    渽
    2.81
     dévelo
    2.59
    诒
    2.58
     zelve
    2.53
    孓
    2.52
    嵎
    2.50
    شتر
    2.45
    ·
    2.45
    Activations Density 0.010%

    No Known Activations