© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98554
    Prev
    Next
    INDEX
    Explanations

    Stackdriver appenders

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

    This neuron detects code identifiers—variable, type, or constant names (typically in uppercase or CamelCase).

    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
    ですが
    -1.76
    しましたが
    -1.65
     borboleta
    -1.62
    がありますが
    -1.55
    elegante
    -1.54
     köln
    -1.52
     dourado
    -1.51
    <bos>
    -1.51
     herido
    -1.49
     mädchen
    -1.48
    POSITIVE LOGITS
    N
    1.72
    D
    1.67
    P
    1.61
    為に
    1.60
    H
    1.55
    R
    1.51
    M
    1.51
    B
    1.49
    O
    1.49
    T
    1.49
    Activations Density 0.043%

    No Known Activations