© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108195
    Prev
    Next
    INDEX
    Explanations

    in terms of

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

    This neuron fires on high-level methodological verbs (like “express,” “describe,” “calculate,” “derive,” “demonstrate”) that introduce the main contributions or results in scientific writing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     zaradi
    -0.81
     played
    -0.78
    essa
    -0.76
     devido
    -0.75
     déposer
    -0.73
    Insta
    -0.73
     لتح
    -0.73
     ממ
    -0.71
     phía
    -0.71
     tijdens
    -0.71
    POSITIVE LOGITS
     terms
    2.48
     in
    2.45
    terms
    1.80
    Terms
    1.45
     términos
    1.41
     Terms
    1.38
     pomocí
    1.16
     termes
    1.15
     термина
    1.11
    TERMS
    1.10
    Activations Density 0.087%

    No Known Activations