© 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. 7448
    Prev
    Next
    INDEX
    Explanations

    configuration flags

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

    The neuron fires on all‐caps code tokens—particularly C/C++ preprocessor macro names and configuration flags.

    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
     utilizados
    -1.84
     what
    -1.80
    などと
    -1.55
     almac
    -1.53
     how
    -1.50
    などに
    -1.45
     pegatina
    -1.45
     utilizado
    -1.45
     tomado
    -1.44
     alfombra
    -1.44
    POSITIVE LOGITS
     of
    2.47
     immense
    1.50
    his
    1.50
    8
    1.49
    not
    1.48
    4
    1.48
    任何
    1.41
    ient
    1.39
    an
    1.39
    6
    1.36
    Activations Density 0.036%

    No Known Activations