© 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. 107663
    Prev
    Next
    INDEX
    Explanations

    case study

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

    The neuron fires on tokens that mark section or list indices (e.g. “directory” in an index listing or standalone numerals like “4”).

    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
     spieg
    -0.98
    "../
    -0.96
    мах
    -0.95
    anderen
    -0.94
     lille
    -0.92
    мар
    -0.92
     cebola
    -0.92
     kato
    -0.91
    ⊕
    -0.90
     laik
    -0.89
    POSITIVE LOGITS
     anklicken
    0.96
    7
    0.91
     exciter
    0.91
     چیه
    0.90
    6
    0.88
    ll
    0.88
    9
    0.87
     içerisinde
    0.86
     ROE
    0.86
    5
    0.86
    Activations Density 0.000%

    No Known Activations