© 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. 11105
    Prev
    Next
    INDEX
    Explanations

    keys or field names

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

    This neuron spotlights programming identifiers and configuration parameter names (often in CamelCase or all caps) within text.

    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
    弊社
    -1.22
    こんばん
    -1.14
    私が
    -1.13
    łgorzata
    -1.09
    当社
    -1.09
    چگونه
    -1.08
    ığım
    -1.08
     Preisen
    -1.07
    Наша
    -1.05
    بهترین
    -1.05
    POSITIVE LOGITS
     of
    1.42
     option
    1.34
     you
    1.27
     section
    1.26
     in
    1.19
     and
    1.16
    section
    1.14
     field
    1.11
     value
    1.10
    -
    1.09
    Activations Density 0.138%

    No Known Activations