© 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. 107266
    Prev
    Next
    INDEX
    Explanations

    technical details or specifications

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

    The neuron strongly activates on punctuation symbols and code/markup delimiters (e.g. braces, commas, periods, quotes) in the text.

    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
     febr
    -0.85
    antonio
    -0.78
    ریح
    -0.75
    ३
    -0.75
     Brownian
    -0.75
     вдруг
    -0.72
     Discrete
    -0.71
    tulo
    -0.71
     hô
    -0.70
     convi
    -0.70
    POSITIVE LOGITS
     jednak
    0.80
     carreteras
    0.77
    摩托
    0.76
    ⇛
    0.76
    ctical
    0.75
     necesitar
    0.74
    ulu
    0.73
    Tyl
    0.72
    kmale
    0.72
     regreso
    0.72
    Activations Density 0.001%

    No Known Activations