© 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. 32843
    Prev
    Next
    INDEX
    Explanations

    restrictions on purpose

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

    The neuron activates on long runs of repeated punctuation characters (like rows of asterisks, equals signs, or other symbols) used as comment separators.

    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
    ="//
    -0.98
    atív
    -0.87
    ]';
    -0.85
     '{@
    -0.84
    ụp
    -0.84
    lichte
    -0.83
     می‌ده
    -0.83
     Frauen
    -0.83
     Vierge
    -0.82
    Читать
    -0.82
    POSITIVE LOGITS
    case
    1.13
     case
    1.09
     SING
    0.88
    了些
    0.85
     molti
    0.84
    tase
    0.82
    fuss
    0.82
    爸爸
    0.81
    落地
    0.80
     caso
    0.79
    Activations Density 0.000%

    No Known Activations