© 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. 58498
    Prev
    Next
    INDEX
    Explanations

    option menu

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

    The neuron chiefly responds to numeric literals (both integers and decimals) in the text.

    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
     between
    -1.45
    </em>
    -1.43
     last
    -1.32
    ҫ
    -1.18
    ốp
    -1.18
    撻
    -1.16
     in
    -1.16
    archiwizowane
    -1.13
     grootste
    -1.13
    〬
    -1.08
    POSITIVE LOGITS
    This
    1.48
     These
    1.41
    If
    1.34
    There
    1.28
     這
    1.27
    These
    1.25
    Following
    1.24
    Since
    1.21
     --
    1.18
    After
    1.18
    Activations Density 0.144%

    No Known Activations