© 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. 15067
    Prev
    Next
    INDEX
    Explanations

    MAVLink timestamp structures

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

    The neuron fires on uppercase code identifiers and macro names (e.g., C preprocessor defines and struct/type 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_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
     their
    -1.80
     like
    -1.73
     create
    -1.67
     for
    -1.63
     more
    -1.62
     most
    -1.53
     or
    -1.52
     creating
    -1.52
     several
    -1.52
     two
    -1.51
    POSITIVE LOGITS
     também
    1.57
     también
    1.48
     tampoco
    1.47
     poë
    1.46
     erhi
    1.42
     humeur
    1.42
     médicaments
    1.40
     aceitar
    1.40
     militer
    1.38
     rapporter
    1.38
    Activations Density 0.011%

    No Known Activations