© 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. 70854
    Prev
    Next
    INDEX
    Explanations

    annual reports and yearly updates

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

    The neuron fires strongly on discourse‐level transition signals—common conjunctions (e.g. “and”), adverbial connectors (e.g. “Additionally”), commas, periods, and other clause‐boundary markers.

    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
    américa
    -1.13
    Когда
    -1.12
    我已经
    -1.11
    ához
    -1.10
    Obrázky
    -1.08
    ából
    -1.08
    மே
    -1.03
     esetén
    -1.03
    ONIC
    -1.03
     Caucasian
    -1.02
    POSITIVE LOGITS
     annual
    1.52
     yearly
    1.34
     year
    1.34
     updates
    1.27
     again
    1.23
     årets
    1.22
     leadership
    1.21
     dianteira
    1.20
     update
    1.20
     our
    1.18
    Activations Density 0.046%

    No Known Activations