© 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. 16190
    Prev
    Next
    INDEX
    Explanations

    graphics and compute libraries

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

    The neuron fires on all-caps programming identifiers (library/framework/API names or macros) in code.

    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
    ledad
    -1.40
     atau
    -1.29
     other
    -1.29
    nees
    -1.28
    alucía
    -1.25
     familien
    -1.22
     our
    -1.21
    vereignty
    -1.21
    zucht
    -1.20
    หรือ
    -1.20
    POSITIVE LOGITS
     it
    1.23
    大半
    1.21
     Hinsicht
    1.13
     Bestandteil
    1.09
    幾乎
    1.09
    B
    1.03
     совершенно
    1.03
     wesentlich
    1.02
    T
    1.02
    L
    1.02
    Activations Density 0.012%

    No Known Activations