© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73773
    Prev
    Next
    INDEX
    Explanations

    six o'clock

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

    The neuron fires on line‐break and indentation tokens, i.e. it’s detecting end-of-line/newline markers (and the surrounding whitespace) in code.

    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
    FAMIL
    -0.81
    アンケート
    -0.79
     premiums
    -0.75
    président
    -0.75
    showcase
    -0.75
     gången
    -0.74
     yakni
    -0.73
    Probable
    -0.72
    Contributors
    -0.71
    ueta
    -0.71
    POSITIVE LOGITS
     gameState
    1.11
     PLAY
    1.02
     wall
    0.93
    ticism
    0.87
    img
    0.85
    database
    0.84
    лих
    0.84
    boy
    0.84
    wall
    0.83
    PRE
    0.82
    Activations Density 0.003%

    No Known Activations