© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102515
    Prev
    Next
    INDEX
    Explanations

    database cursor execute

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

    method calls or function invocations in programming code, particularly object methods using dot notation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron flags mentions of graphics‐drawing context APIs and their associated calls (e.g. CGContext/CanvasRenderingContext2D methods).

    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
     позволяет
    -1.47
    ítez
    -1.36
     outras
    -1.32
     preghi
    -1.32
    齧
    -1.31
    でお
    -1.30
     Erster
    -1.29
     других
    -1.27
     spus
    -1.26
     entraî
    -1.25
    POSITIVE LOGITS
     ataupun
    1.42
    क्या
    1.36
    %"),
    1.34
    Kā
    1.34
    ي
    1.28
    그러나
    1.25
     tuyau
    1.25
    »)
    1.25
    きます
    1.23
    messungen
    1.21
    Activations Density 0.003%

    No Known Activations