© 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. 68131
    Prev
    Next
    INDEX
    Explanations

    app prefix

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

    The neuron fires on the token “app,” i.e. it detects occurrences of the substring “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_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
     It
    -2.95
     promove
    -2.27
    心底
    -2.25
    ть
    -2.09
     of
    -2.08
    </b>
    -2.08
     To
    -2.08
    だけでなく
    -2.02
     its
    -1.96
    だけではなく
    -1.95
    POSITIVE LOGITS
    app
    2.97
    巿
    2.78
     enticing
    2.41
     unrelenting
    2.22
    اء
    2.13
    壟
    2.13
     ominous
    2.11
     інші
    2.11
     undeniably
    2.11
     eight
    2.09
    Activations Density 0.015%

    No Known Activations