© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86132
    Prev
    Next
    INDEX
    Explanations

    any or anyone

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

    The neuron fires on runs of non‐alphanumeric symbols and punctuation (e.g., sequences of dots, colons, tildes, backslashes, escape codes, and similar characters).

    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
     but
    -1.66
    zembro
    -1.52
    They
    -1.46
    Rather
    -1.44
    Through
    -1.38
    Without
    -1.34
    ́t
    -1.34
    fling
    -1.32
     animés
    -1.29
    Should
    -1.27
    POSITIVE LOGITS
     any
    1.28
     variété
    1.28
    癭
    1.23
     infância
    1.22
     anyone
    1.17
     terão
    1.13
    
    1.12
     have
    1.10
     many
    1.09
     événement
    1.09
    Activations Density 0.020%

    No Known Activations