© 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. 22-GEMMASCOPE-RES-131K
    7. 16545
    Prev
    Next
    INDEX
    Explanations

    coding and specific concepts

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

    The neuron flags code identifiers—especially API/library class or function names (e.g. PascalCase or camelCase tokens) in source files.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     lixo
    -1.02
     specific
    -1.01
     its
    -0.99
     better
    -0.99
     certain
    -0.98
     erläut
    -0.98
     prior
    -0.97
    empresas
    -0.96
     specified
    -0.94
     simply
    -0.93
    POSITIVE LOGITS
     WINE
    1.14
    weist
    1.14
     pylori
    1.13
     bentuk
    1.12
    ídio
    1.09
     tamaños
    1.05
    🛏
    1.02
    lamo
    1.02
    FOL
    1.02
    thical
    1.01
    Activations Density 0.001%

    No Known Activations