© 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. 72728
    Prev
    Next
    INDEX
    Explanations

    UI elements, code snippets

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

    This neuron fires on programming identifiers (e.g. class, property, or API names) in code snippets.

    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
     into
    -1.02
     details
    -1.01
     princípios
    -0.99
     estudia
    -0.98
     afferma
    -0.98
     türkiye
    -0.97
    gangss
    -0.97
    šne
    -0.96
     conteúdos
    -0.96
    Welke
    -0.96
    POSITIVE LOGITS
     NOT
    1.05
    顶级
    1.01
     ALL
    1.00
     ONE
    0.96
     persecu
    0.96
     hivyo
    0.93
    aliyun
    0.92
    TProtocol
    0.91
    omiast
    0.91
     אֲ
    0.90
    Activations Density 0.000%

    No Known Activations