© 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. 10-GEMMASCOPE-RES-131K
    7. 72108
    Prev
    Next
    INDEX
    Explanations

    model database entity names

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

    The neuron fires on domain-specific identifiers (class, entity, table, or field names) in code or schema definitions.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     even
    -1.30
     or
    -1.17
     at
    -1.14
    UVEN
    -1.07
     لله
    -1.04
     Even
    -1.02
    Even
    -1.02
    During
    -1.00
     интерьере
    -1.00
    贄
    -0.99
    POSITIVE LOGITS
     também
    1.50
    はこの
    1.42
    
    1.38
     cũng
    1.31
     about
    1.24
     FormBuilder
    1.24
     diferentes
    1.23
     différentes
    1.23
     órganos
    1.21
    cje
    1.19
    Activations Density 0.103%

    No Known Activations