© 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. 98187
    Prev
    Next
    INDEX
    Explanations

    processes and relationships

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

    The neuron fires on document tokens that represent numeric or structured references—e.g. section numbers, measurements, percentages, hyphens in labeled steps or technical data.

    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
     each
    -0.83
     those
    -0.81
    andafter
    -0.77
    ปัญ
    -0.77
    quatch
    -0.76
     this
    -0.76
     Quij
    -0.75
    Lives
    -0.75
    differences
    -0.75
     satisfecho
    -0.74
    POSITIVE LOGITS
    不管是
    0.84
    ６
    0.82
     โดย
    0.82
     POLIT
    0.82
    和
    0.82
    equals
    0.81
     chronicle
    0.79
    私が
    0.79
     любое
    0.79
    От
    0.78
    Activations Density 0.185%

    No Known Activations