© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38358
    Prev
    Next
    INDEX
    Explanations

    FIG. illustration following

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

    The neuron fires on structural/documentation markers—words used in headings, figure captions, and code/property declarations (e.g. “FIG.,” “illustrates,” “depicts,” “property”).

    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
     even
    -1.55
     from
    -1.16
     will
    -1.13
     without
    -1.12
     and
    -1.04
     ета
    -1.02
     actually
    -1.01
    bren
    -1.01
     this
    -0.99
     also
    -0.99
    POSITIVE LOGITS
    取决
    1.28
     áng
    1.19
     ouvrir
    1.16
    küche
    1.16
     ず
    1.16
    Lø
    1.11
    allowing
    1.11
     zincir
    1.10
     bewertet
    1.09
    introdu
    1.08
    Activations Density 0.001%

    No Known Activations