© 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. 34883
    Prev
    Next
    INDEX
    Explanations

    API operation summaries

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

    The neuron fires on standalone numeric tokens (numbers or digit sequences).

    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
     Firestone
    -0.91
     భూ
    -0.79
    ريف
    -0.79
     exacta
    -0.71
    ULOS
    -0.71
     보고
    -0.70
     SPM
    -0.69
     конвер
    -0.69
    PROV
    -0.68
     décid
    -0.68
    POSITIVE LOGITS
     summary
    1.28
     operation
    1.25
     Operation
    1.21
    summary
    1.11
    Operation
    1.10
     responses
    1.02
     tags
    1.02
    operation
    0.98
     response
    0.98
     operations
    0.98
    Activations Density 0.029%

    No Known Activations