© 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. 34106
    Prev
    Next
    INDEX
    Explanations

    android activity and dialogs

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

    The neuron strongly activates on the token “app” when it appears as part of Android package or import paths (e.g. “android.app” or “android.support.v7.app”).

    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
    赑
    -1.40
     prestazioni
    -1.38
     Geografía
    -1.36
     alcuni
    -1.36
    qtt
    -1.30
    槎
    -1.28
     dão
    -1.27
    ᯾
    -1.27
     alcune
    -1.25
    INSON
    -1.25
    POSITIVE LOGITS
    Before
    1.32
    At
    1.32
    While
    1.28
    ↵↵
    1.26
    Like
    1.23
    For
    1.18
    All
    1.17
    Despite
    1.17
    As
    1.16
    Without
    1.16
    Activations Density 0.001%

    No Known Activations