© 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. 10-GEMMASCOPE-RES-131K
    4. 130371
    Prev
    Next
    INDEX
    Explanations

    index file paths

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

    The neuron fires on numeric tokens—especially numbers in file‐name or URL fragments (e.g. “index 346,” “318,” “304,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    0
    -1.69
     to
    -1.66
     nejen
    -1.58
     ikke
    -1.58
    だけではなく
    -1.52
     yalnızca
    -1.52
    EL
    -1.50
     
    -1.49
    AN
    -1.47
     aquela
    -1.47
    POSITIVE LOGITS
    ଃ
    1.59
    💟
    1.52
     SSSR
    1.52
     tuta
    1.50
    Q
    1.45
    🖖
    1.43
    🩷
    1.42
    Donativos
    1.42
    parently
    1.41
     寸
    1.41
    Activations Density 0.017%

    No Known Activations