© 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. 92566
    Prev
    Next
    INDEX
    Explanations

    Providing free

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

    This neuron fires on CSS‐ or style‐sheet–like declarations, especially color and style property names (e.g. “foreground”, “background”, “cursor Color”) and their associated numeric or hex values.

    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
     strada
    -0.78
     boletín
    -0.71
    ENTES
    -0.71
    を整
    -0.68
     professionnels
    -0.68
     progressive
    -0.68
     conduire
    -0.67
     découvertes
    -0.67
     geloof
    -0.66
    zzar
    -0.66
    POSITIVE LOGITS
     WP
    0.84
    黑
    0.83
    ♟
    0.81
     Kirke
    0.81
     décédé
    0.77
    役
    0.76
     Episodes
    0.75
     alu
    0.75
     planes
    0.75
     foreground
    0.74
    Activations Density 0.025%

    No Known Activations