© 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. 10-GEMMASCOPE-RES-131K
    7. 85349
    Prev
    Next
    INDEX
    Explanations

    code structure and configuration

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

    The neuron flags programming identifiers—especially uppercase API/class/property 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_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
     for
    -1.95
     that
    -1.61
     in
    -1.53
     this
    -1.51
     should
    -1.47
     kesadaran
    -1.44
     because
    -1.41
     it
    -1.38
     sollten
    -1.37
     regardless
    -1.35
    POSITIVE LOGITS
    又在
    1.38
    Kf
    1.28
     artistico
    1.25
    ≲
    1.23
    ₦
    1.23
     Leopard
    1.21
     筆
    1.14
    筰
    1.14
     твои
    1.14
     другое
    1.13
    Activations Density 0.028%

    No Known Activations