© 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. 34501
    Prev
    Next
    INDEX
    Explanations

    code comments and identifiers

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

    This neuron strongly activates on path segments in Angular component metadata, i.e. the file names (like “product-suggestion.component.scss” and “.html”) in the styleUrls and templateUrl declarations.

    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
    axl
    -1.23
     perdió
    -1.22
     Temos
    -1.19
     ocorrer
    -1.13
     cayó
    -1.13
    頬
    -1.12
    razer
    -1.11
    kraine
    -1.10
    <blockquote>
    -1.07
    lessed
    -1.06
    POSITIVE LOGITS
     at
    1.37
     as
    1.20
    基本的
    1.09
     on
    1.09
     one
    1.08
    //<
    1.07
     from
    1.05
     probably
    1.02
     although
    1.01
    vieja
    0.99
    Activations Density 0.001%

    No Known Activations