© 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. 465
    Prev
    Next
    INDEX
    Explanations

    led by or coached by

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

    This neuron detects colon characters (":") that introduce code directives, parameters, or metadata in programming and documentation contexts.

    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
    ueur
    -0.75
     miejs
    -0.68
    FEATURE
    -0.68
    ویژگی
    -0.67
     neve
    -0.66
    taken
    -0.66
    stad
    -0.66
     polyps
    -0.66
     crayon
    -0.66
     REMOVE
    -0.66
    POSITIVE LOGITS
     здоровья
    0.66
     phosphorus
    0.62
     from
    0.61
     Phosphorus
    0.60
     Wildlife
    0.60
    bouncycastle
    0.60
     doctrines
    0.59
     thinks
    0.59
    Contacts
    0.59
     rowspan
    0.59
    Activations Density 0.058%

    No Known Activations