© 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. 102431
    Prev
    Next
    INDEX
    Explanations

    documentation special characters

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

    The neuron is looking for colon tokens (":"), especially those used in code/type annotations or markup.

    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
     interpol
    -0.82
    Roland
    -0.82
    alak
    -0.81
     Brute
    -0.81
     appa
    -0.81
     miniatur
    -0.79
    rago
    -0.77
     propo
    -0.77
    chieben
    -0.77
     panorama
    -0.74
    POSITIVE LOGITS
     type
    1.50
    return
    1.30
    type
    1.22
    param
    1.12
     TYPE
    1.01
    Type
    0.98
     types
    0.96
     typu
    0.95
    TYPE
    0.94
     return
    0.93
    Activations Density 0.006%

    No Known Activations