© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62643
    Prev
    Next
    INDEX
    Explanations

    types and classifications

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

    The neuron fires on long, multi-syllable technical or scientific jargon (e.g. specialized terminology).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     laim
    -0.83
     atmosfer
    -0.75
    preference
    -0.74
     Pute
    -0.74
    ͘
    -0.73
    ldr
    -0.72
     spion
    -0.71
    nego
    -0.71
     Schröder
    -0.70
    oder
    -0.70
    POSITIVE LOGITS
     type
    1.65
     Type
    1.45
     constitution
    1.32
     constitutions
    1.30
     típus
    1.29
    Type
    1.24
    TYPE
    1.20
    getType
    1.18
     TYPE
    1.17
     constitutional
    1.17
    Activations Density 0.039%

    No Known Activations