© 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. 22-GEMMASCOPE-RES-131K
    4. 39349
    Prev
    Next
    INDEX
    Explanations

    gambling, Adele, Use, Fernandez

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

    This neuron detects code‐style punctuation and type markers—especially parentheses, brackets, and standalone uppercase type tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    !(
    -1.23
     their
    -1.23
     who
    -1.09
     और
    -1.08
     où
    -1.07
     الحالي
    -1.07
    ׇ
    -1.04
     only
    -1.01
    喩
    -1.01
    繭
    -1.00
    POSITIVE LOGITS
    を探す
    1.40
    tells
    1.36
    garlic
    1.34
     supuestamente
    1.34
    ところです
    1.34
    wasn
    1.33
    offers
    1.31
    continues
    1.27
    knows
    1.26
     мужская
    1.24
    Activations Density 0.001%

    No Known Activations