© 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. 10-GEMMASCOPE-RES-131K
    7. 85070
    Prev
    Next
    INDEX
    Explanations

    code snippets and formatting

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

    The neuron fires on tokens that consist of or end with special punctuation characters (especially “%” or “}”), i.e. code-based format placeholders and similar symbols.

    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
     .
    -2.95
    \
    -2.83
    ()
    -2.64
    (
    -2.64
    ,
    -2.59
    ("
    -2.50
     The
    -2.44
    ``
    -2.36
     ''
    -2.36
    9
    -2.34
    POSITIVE LOGITS
    ’,
    2.97
    ?
    2.67
     puteți
    2.52
    ’?
    2.42
    )\}$
    2.39
    ′-
    2.38
    ጵ
    2.38
    ложить
    2.30
    僂
    2.28
    婬
    2.27
    Activations Density 0.004%

    No Known Activations