© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98210
    Prev
    Next
    INDEX
    Explanations

    specific nouns followed by descriptive phrasing

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

    This neuron flags the main subject nouns (like car, wheels, track, hill, matches, championship) that denote the central objects in math and physics problem statements.

    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
     mascarilla
    -1.23
    ὓ
    -1.23
    heren
    -1.23
     sièges
    -1.20
     erreurs
    -1.17
    kyrie
    -1.16
     véritables
    -1.15
     améli
    -1.15
     itinéraires
    -1.13
     apporter
    -1.11
    POSITIVE LOGITS
     this
    2.28
     with
    1.90
     these
    1.68
     at
    1.48
     if
    1.39
     each
    1.34
     for
    1.28
     should
    1.23
     tersebut
    1.20
     using
    1.19
    Activations Density 0.054%

    No Known Activations