© 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. 9930
    Prev
    Next
    INDEX
    Explanations

    court proceedings

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

    This neuron activates on relatively rare, semantically rich content words (nouns, verbs, or adjectives) rather than on common function words.

    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
    ↵↵
    -1.80
     were
    -1.48
    ↵↵↵
    -1.48
     there
    -1.40
     posibilidades
    -1.35
    begin
    -1.34
     would
    -1.26
    </tr>
    -1.23
    ↵↵↵↵
    -1.20
    また
    -1.18
    POSITIVE LOGITS
     diesen
    1.45
     settimane
    1.38
     Architekten
    1.27
     ว่า
    1.27
    digen
    1.24
    vismo
    1.23
     giudice
    1.23
    amerikanischer
    1.23
     vescovo
    1.23
     dage
    1.23
    Activations Density 0.005%

    No Known Activations