© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57899
    Prev
    Next
    INDEX
    Explanations

    programming and styling contexts

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

    This neuron detects backslashes used as namespace or path separators (e.g., in fully qualified class or module names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    chaikovsky
    -0.80
    压力
    -0.77
    Speaker
    -0.75
    BACK
    -0.71
    NUM
    -0.70
    Pessoa
    -0.70
     Pressure
    -0.69
     बच्च
    -0.69
    Pressure
    -0.69
    誨
    -0.68
    POSITIVE LOGITS
    "=>$
    0.89
    Emoji
    0.85
     emoji
    0.84
     Emoji
    0.81
    confined
    0.81
     COMPAN
    0.77
     styling
    0.77
     style
    0.74
    confirm
    0.74
     confided
    0.73
    Activations Density 0.026%

    No Known Activations