© 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. 39495
    Prev
    Next
    INDEX
    Explanations

    code delimiters and documentation start

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

    This neuron fires on literal asterisk tokens (e.g. “*” or “**”) used as formatting or list markers in markup (Markdown/Swagger/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_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
     all
    -1.29
     you
    -1.27
     then
    -1.25
     where
    -1.21
     only
    -1.20
     their
    -1.15
     just
    -1.12
     られる
    -1.12
     even
    -1.12
     especially
    -1.09
    POSITIVE LOGITS
     inond
    1.31
     комплекте
    1.08
    ۪
    1.07
    another
    1.06
    ⑊
    1.02
     presos
    0.98
     cinqu
    0.98
     poser
    0.98
    additional
    0.97
     systé
    0.96
    Activations Density 0.003%

    No Known Activations