© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50354
    Prev
    Next
    INDEX
    Explanations

    list items or descriptions

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

    The neuron activates on the asterisk character used as a bullet or comment marker (e.g. the leading “*” in code comment blocks).

    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
     nede
    -0.97
     rios
    -0.95
     péro
    -0.94
     jesu
    -0.93
     brille
    -0.92
     menging
    -0.92
     hunde
    -0.91
     alarme
    -0.91
     correctes
    -0.90
     judicia
    -0.90
    POSITIVE LOGITS
     value
    0.86
    bori
    0.83
     new
    0.83
     resourceCulture
    0.81
    Remover
    0.77
     suele
    0.77
     öst
    0.76
     pursuits
    0.75
     copertura
    0.75
    侄
    0.75
    Activations Density 0.000%

    No Known Activations