© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73478
    Prev
    Next
    INDEX
    Explanations

    systems of interacting parts or relationships

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

    The neuron consistently fires on the head noun of multi‐word technical or scientific compound terms (e.g. “factor,” “promoter,” “complex,” “system,” “center,” “element,” “listener,” etc.).

    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
     to
    -1.10
    lesias
    -1.08
    身边的
    -0.98
    婓
    -0.93
    Música
    -0.93
    Matri
    -0.93
    スズキ
    -0.93
     different
    -0.92
    まさかの
    -0.91
    fiques
    -0.91
    POSITIVE LOGITS
     combo
    1.21
    unno
    1.17
     interaction
    1.17
     equation
    1.12
    signee
    1.11
     relationship
    1.09
    nadequate
    1.09
     combination
    1.08
     וכל
    1.05
     type
    1.05
    Activations Density 0.084%

    No Known Activations