© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14272
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and file declarations

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

    This neuron fires on tokens that name file formats, frameworks, or libraries (e.g. “xaml,” “presentation,” “web,” “xhtml,” “helmet,” “browser,” “UIKit,” “js”).

    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
    ation
    -1.21
    ?"
    -1.16
     aDecoder
    -1.15
     seems
    -1.14
    無し
    -1.12
     With
    -1.11
     says
    -1.09
     or
    -1.09
     a
    -1.09
     from
    -1.05
    POSITIVE LOGITS
    Baz
    1.16
    Vri
    1.16
    Bjs
    1.16
     afore
    1.14
    Cek
    1.13
    ANTAGE
    1.13
    Ponto
    1.13
    啖
    1.12
    rógeno
    1.10
    <bos>
    1.09
    Activations Density 0.001%

    No Known Activations