© 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. 22-GEMMASCOPE-RES-131K
    7. 38365
    Prev
    Next
    INDEX
    Explanations

    code comment start"""

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

    This neuron doesn’t respond to any tokens—it effectively finds nothing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     one
    -1.69
     what
    -1.15
     by
    -1.14
     What
    -1.11
     not
    -1.11
     such
    -1.11
     In
    -1.02
    In
    -0.98
     people
    -0.96
    Slf
    -0.94
    POSITIVE LOGITS
    rufen
    1.08
    oğlu
    0.96
     indien
    0.95
     mooi
    0.95
    août
    0.94
     rijk
    0.94
     taşlı
    0.94
     satılık
    0.93
     güne
    0.93
     ถ้า
    0.93
    Activations Density 0.003%

    No Known Activations