© 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. 84444
    Prev
    Next
    INDEX
    Explanations

    data identifiers

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

    This neuron detects mentions of specific numeric identifiers or parameters (e.g., page or ID numbers).

    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
     lança
    -1.17
     města
    -1.14
     cumplido
    -1.12
    গু
    -1.12
     '".$
    -1.11
    regarding
    -1.11
     Herrschaft
    -1.11
    wherein
    -1.10
     sufrido
    -1.10
     Seahawks
    -1.09
    POSITIVE LOGITS
     from
    2.05
     that
    1.48
     information
    1.48
     in
    1.41
     as
    1.38
    を
    1.22
     via
    1.20
     if
    1.12
     on
    1.11
     which
    1.09
    Activations Density 0.131%

    No Known Activations