© 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. 10-GEMMASCOPE-RES-131K
    7. 21643
    Prev
    Next
    INDEX
    Explanations

    Cloudera, Joung, File, unzip

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

    The neuron selectively activates on technical or code‐related tokens such as command names, exception class names, company or project names (e.g. “Clou…,” “FileNotFound”), and filesystem shorthand like “~/”.

    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
    G
    -3.25
    r
    -3.00
    J
    -2.89
    U
    -2.86
    F
    -2.80
    ୌ
    -2.58
     tyd
    -2.56
    V
    -2.53
    たち
    -2.52
     ؟
    -2.50
    POSITIVE LOGITS
                    
    2.86
    </strong>
    2.84
    り
    2.38
     resembled
    2.36
        
    2.31
    他有
    2.23
     resembles
    2.22
     bein
    2.16
     conquête
    2.11
    laboration
    2.09
    Activations Density 0.012%

    No Known Activations