© 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. 84443
    Prev
    Next
    INDEX
    Explanations

    scientific publications

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

    references to academic publications in scientific or technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects bibliographic citation headings (e.g. “Proceedings,” “Trans,” journal or conference title tokens).

    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
    そして
    -1.25
     Erwart
    -1.24
     Voraussetzung
    -1.23
     новых
    -1.23
     procéder
    -1.21
     circunstancia
    -1.20
    が無い
    -1.16
     Asegúrese
    -1.13
    tät
    -1.13
     pratiquer
    -1.13
    POSITIVE LOGITS
    -
    1.30
    </em>
    1.29
     Even
    1.14
    ,
    1.09
     Scott
    1.06
     or
    1.06
    živ
    1.06
     (
    1.03
     Unlike
    1.02
     ligeramente
    1.01
    Activations Density 0.004%

    No Known Activations