© 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. 20121
    Prev
    Next
    INDEX
    Explanations

    scan devices or directories

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

    This neuron activates on occurrences of “scan” (in any capitalization or inflected form such as “Scan” or “scanning”).

    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
     คือ
    -2.02
    
    -1.98
     dicen
    -1.97
     nef
    -1.87
    킁
    -1.83
    컹
    -1.79
    卺
    -1.78
     ܙ
    -1.78
     Infór
    -1.77
     bele
    -1.77
    POSITIVE LOGITS
    able
    2.16
     This
    2.16
    e
    2.09
     reputable
    2.03
    $
    1.99
     this
    1.92
     intense
    1.90
     extraordinarily
    1.88
     revolutionary
    1.87
    -
    1.86
    Activations Density 0.008%

    No Known Activations