© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13777
    Prev
    Next
    INDEX
    Explanations

    academic citations and abbreviations

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

    The neuron primarily picks out numeric tokens (e.g. reference IDs or numeric 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_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
     any
    -1.88
     using
    -1.84
     out
    -1.76
    Taking
    -1.74
     new
    -1.74
     time
    -1.73
     three
    -1.72
    Despite
    -1.70
     on
    -1.69
     one
    -1.69
    POSITIVE LOGITS
     Dinas
    1.73
     ........
    1.69
    😊
    1.63
    ments
    1.63
     "-"
    1.57
     .......
    1.56
    ment
    1.55
    romeda
    1.53
     "*
    1.53
    to
    1.53
    Activations Density 0.243%

    No Known Activations