© 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. 34-GEMMASCOPE-RES-131K
    7. 12033
    Prev
    Next
    INDEX
    Explanations

    URLs and file extensions

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

    The neuron fires on numeric tokens (especially multi‐digit numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     source
    -0.85
     opty
    -0.76
    source
    -0.74
    Src
    -0.72
    Source
    -0.71
     sources
    -0.68
    uchung
    -0.68
     factor
    -0.67
    sourceforge
    -0.67
    หลวง
    -0.67
    POSITIVE LOGITS
     remol
    0.79
    ስ
    0.77
    Pause
    0.70
    ЧЕ
    0.68
     échelle
    0.67
     PATCH
    0.66
     exti
    0.66
     technic
    0.65
    казать
    0.65
    鰆
    0.65
    Activations Density 0.079%

    No Known Activations