© 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. 67057
    Prev
    Next
    INDEX
    Explanations

    UI elements and text labels

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

    This neuron activates on Android/Java code identifiers that name UI widget fields (e.g. txtUsuario, btnLogin, lblMensaje).

    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
     is
    -1.22
    Generally
    -1.20
     since
    -1.17
     there
    -1.16
     our
    -1.11
     produced
    -1.09
     because
    -1.09
    Komentar
    -1.09
    Typically
    -1.09
     these
    -1.05
    POSITIVE LOGITS
     vraiment
    1.10
    []);
    1.08
     maintenant
    1.08
     heute
    1.04
    nitz
    1.02
    چی
    1.02
    //{
    1.02
    泺
    1.00
     capito
    1.00
    adero
    1.00
    Activations Density 0.008%

    No Known Activations