© 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. 73529
    Prev
    Next
    INDEX
    Explanations

    result nouns

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

    The neuron selectively fires on long, multi-syllable technical or abstract noun phrases (e.g. domain-specific jargon and nominalizations).

    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
    _
    -1.00
     The
    -0.98
                         
    -0.97
    of
    -0.97
     int
    -0.97
     If
    -0.96
    ((
    -0.96
    c
    -0.96
    so
    -0.95
    pos
    -0.94
    POSITIVE LOGITS
     菇
    1.10
     boute
    1.06
     embre
    1.03
    ૐ
    1.03
     éx
    1.03
     vrijdag
    1.02
     felpa
    1.01
    龑
    1.00
     parachoque
    1.00
    綃
    0.99
    Activations Density 3.466%

    No Known Activations