© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9498
    Prev
    Next
    INDEX
    Explanations

    followed by noun

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

    The neuron fires on the substring “By” in identifiers (e.g. in CamelCase method or function names).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     что
    -2.05
    ,
    -1.77
     новая
    -1.75
    >
    -1.73
    ErrUnexpectedEOF
    -1.69
    ábado
    -1.61
    是我的
    -1.59
    !
    -1.56
    erialized
    -1.56
     albeit
    -1.55
    POSITIVE LOGITS
     virtue
    1.60
    沇
    1.57
     your
    1.55
     Vainqueur
    1.47
     its
    1.46
    outh
    1.44
     recommandée
    1.43
    u
    1.41
    i
    1.41
    őség
    1.41
    Activations Density 0.005%

    No Known Activations