© 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. 22-GEMMASCOPE-RES-131K
    7. 28629
    Prev
    Next
    INDEX
    Explanations

    Comparison Shock absorbers

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

    The neuron fires on the commas that separate numeric or hexadecimal literals in raw data and code array initializers.

    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
    Although
    -1.49
    Zubereitung
    -1.34
    Crítica
    -1.34
    Leírás
    -1.33
    Without
    -1.32
    Though
    -1.32
    Since
    -1.32
    Several
    -1.31
    because
    -1.30
    although
    -1.30
    POSITIVE LOGITS
    '
    1.34
    /***
    1.20
     amd
    1.19
     a
    1.16
    ,
    1.12
     stattfinden
    1.11
    ak
    1.10
    ar
    1.09
    之家
    1.09
    T
    1.08
    Activations Density 0.000%

    No Known Activations