© 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. 112872
    Prev
    Next
    INDEX
    Explanations

    Toolbar and Layout keywords

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

    The neuron strongly activates on occurrences of the Android UI class name “Toolbar” in code snippets.

    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
    🧌
    -1.70
     berkualitas
    -1.64
     favoritas
    -1.64
     sentimentos
    -1.61
     ſou
    -1.59
    ᠌
    -1.59
     Efek
    -1.58
    嚒
    -1.57
    ᥫ
    -1.56
    🫅
    -1.56
    POSITIVE LOGITS
    <i>
    1.83
    <td>
    1.69
    _
    1.60
     Some
    1.59
    he
    1.59
    as
    1.58
    ...
    1.58
     following
    1.55
     r
    1.50
    *
    1.48
    Activations Density 0.003%

    No Known Activations