© 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. 38904
    Prev
    Next
    INDEX
    Explanations

    android appcompat

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

    The neuron fires on occurrences of the token “AppCompat,” i.e. references to the Android AppCompat support library class.

    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
    ↵↵
    -3.16
     strenuous
    -2.53
     \&
    -2.47
    หรือ
    -2.41
     行っ
    -2.38
     idyllic
    -2.31
    iconductors
    -2.30
     первая
    -2.23
     perils
    -2.16
     \#
    -2.14
    POSITIVE LOGITS
    ne
    3.14
    at
    2.78
    The
    2.73
    s
    2.72
     –
    2.69
    by
    2.66
    h
    2.66
    un
    2.59
    酲
    2.58
     kanak
    2.44
    Activations Density 0.001%

    No Known Activations