© 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. 74500
    Prev
    Next
    INDEX
    Explanations

    level indicator

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

    The neuron is triggered by occurrences of the term “level” (including hyphenated or compound uses like “level-set” or “log level”) in code or config contexts.

    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
    
    -1.99
    ↵↵
    -1.97
    霂
    -1.90
    篳
    -1.87
    wanzig
    -1.85
    笮
    -1.80
     glaring
    -1.74
     从
    -1.74
    捭
    -1.74
     jälkeen
    -1.71
    POSITIVE LOGITS
     его
    2.23
    ?"
    2.20
    )
    2.16
    !"
    2.06
     уровень
    2.00
    暃
    1.98
    .'
    1.92
    凩
    1.91
    .
    1.90
    での
    1.89
    Activations Density 0.053%

    No Known Activations