© 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. 15119
    Prev
    Next
    INDEX
    Explanations

    general or normal characteristics

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

    This neuron detects C++ template instantiations and scope‐resolution identifiers (e.g. the “SoftmaxLayer<…>::LayerSetUp” pattern).

    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
    azas
    -0.90
    azer
    -0.85
    bsen
    -0.79
    illaume
    -0.78
    unzi
    -0.77
    Either
    -0.76
    unta
    -0.75
    кут
    -0.73
    Thrown
    -0.73
    Odkazy
    -0.73
    POSITIVE LOGITS
     general
    1.18
     normale
    1.03
    普通
    1.02
     обы
    0.96
     normal
    0.92
     generally
    0.91
     characteristics
    0.90
     일반
    0.89
    一般的
    0.89
     with
    0.88
    Activations Density 0.034%

    No Known Activations