© 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. 35817
    Prev
    Next
    INDEX
    Explanations

    quantifiable states or actions

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

    The neuron detects numeric tokens—numbers or numeric measurements (e.g. counts, percentages, and decimal 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
     может
    -1.01
     modified
    -0.98
     their
    -0.98
     われ
    -0.94
     modify
    -0.94
     kwargs
    -0.94
    各种
    -0.93
     changed
    -0.92
    աքին
    -0.92
    伱
    -0.92
    POSITIVE LOGITS
     DECEMBER
    0.96
     NOVEMBER
    0.91
    >${
    0.91
    Texas
    0.90
     Bereits
    0.89
     праздни
    0.88
     March
    0.88
     productores
    0.87
     December
    0.85
    žad
    0.85
    Activations Density 0.046%

    No Known Activations