© 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. 87259
    Prev
    Next
    INDEX
    Explanations

    places, people, and domains

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

    This neuron selectively fires on tokens that are part of headings or titles (including capitalized technical terms, proper nouns, and numbers) rather than in running 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_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
     your
    -1.47
     for
    -1.45
     $
    -1.30
     That
    -1.30
     Not
    -1.27
     people
    -1.26
     let
    -1.26
     on
    -1.25
     give
    -1.25
     bring
    -1.23
    POSITIVE LOGITS
     alho
    1.64
     proteine
    1.31
    不断的
    1.31
    렝
    1.30
     varier
    1.30
     visualiser
    1.30
     medici
    1.28
     candidats
    1.28
    骜
    1.25
     réponse
    1.24
    Activations Density 0.507%

    No Known Activations