© 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. 129891
    Prev
    Next
    INDEX
    Explanations

    usercontent, Deloitte, LoggerFactory,readFile

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

    The neuron fires on occurrences of the identifier “LoggerFactory,” i.e. it detects references to that Java logging factory class.

    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
    馐
    -2.88
     ผม
    -2.86
     또는
    -2.66
     事例
    -2.66
    ญี่ป
    -2.52
    玙
    -2.45
    
    -2.42
    
    -2.42
     verbess
    -2.38
    涐
    -2.36
    POSITIVE LOGITS
     successes
    2.64
    <i>
    2.61
     crée
    2.25
    -
    2.22
    ↵↵
    2.13
    ピアス
    2.11
    ができる
    2.09
     desiring
    2.08
     mantener
    2.08
    </sub>
    2.08
    Activations Density 0.001%

    No Known Activations