© 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. 22-GEMMASCOPE-RES-131K
    7. 33822
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

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

    The neuron activates on occurrences of the Android “appcompat” support‐library token in XML resource paths.

    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
     its
    -1.31
    ofag
    -1.30
     borracha
    -1.30
    ILayout
    -1.30
     piedras
    -1.27
    の方は
    -1.24
     músicos
    -1.23
    ENTINA
    -1.22
    chaise
    -1.21
    xty
    -1.20
    POSITIVE LOGITS
    ちなみに
    1.50
    </b>
    1.44
    <bos>
    1.43
    Rispondi
    1.37
    especially
    1.32
    Зміст
    1.28
    尤其是
    1.27
    in
    1.24
     herrera
    1.24
    ですが
    1.23
    Activations Density 0.000%

    No Known Activations