© 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. 15249
    Prev
    Next
    INDEX
    Explanations

    strategy, loan, era, mutations, room

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

    The neuron fires on specialized jargon or formal topic labels (i.e. domain-specific technical or proper-noun terms).

    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
     phénom
    -1.29
    ᱾
    -1.22
    ॠ
    -1.21
     dramatique
    -1.20
     vagy
    -1.20
    smöglichkeiten
    -1.17
     juzg
    -1.17
    Какво
    -1.17
    éroport
    -1.15
     perang
    -1.15
    POSITIVE LOGITS
     themed
    1.22
    i
    1.12
    M
    1.09
    C
    1.02
    H
    1.00
     I
    0.97
    #
    0.96
    X
    0.93
    циали
    0.91
     &
    0.91
    Activations Density 0.154%

    No Known Activations