© 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. 22-GEMMASCOPE-RES-131K
    4. 36052
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and measurements

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

    This neuron is effectively inactive and does not respond to any tokens.

    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
    0
    -2.16
    覿
    -1.74
     écran
    -1.70
     permettent
    -1.69
     ۱۷
    -1.66
    は
    -1.66
    $
    -1.63
     ――――
    -1.61
     ۱۸
    -1.61
    3
    -1.59
    POSITIVE LOGITS
     because
    1.97
     before
    1.90
     have
    1.88
     when
    1.88
     making
    1.84
     while
    1.77
    aiuto
    1.72
     and
    1.70
     using
    1.68
     first
    1.67
    Activations Density 0.146%

    No Known Activations