© 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. 10-GEMMASCOPE-RES-131K
    7. 73654
    Prev
    Next
    INDEX
    Explanations

    input fields

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

    This neuron fires on mentions of text‐input widget class names (e.g. EditText, LineEdit/QLineEdit) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     durante
    -1.49
    operate
    -1.47
     VERY
    -1.46
    very
    -1.36
    extremely
    -1.35
     enorme
    -1.31
    崀
    -1.29
    笮
    -1.24
     vivent
    -1.24
     dando
    -1.20
    POSITIVE LOGITS
     for
    1.64
     before
    1.53
     from
    1.33
     nestled
    1.24
     your
    1.16
     Reglamento
    1.13
     haphazard
    1.11
     burgeoning
    1.09
     juez
    1.09
     perlindungan
    1.09
    Activations Density 0.034%

    No Known Activations