© 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. 102666
    Prev
    Next
    INDEX
    Explanations

    references to places

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

    The neuron activates on numeric tokens (integers or decimals).

    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
     ustal
    -1.37
     скриншот
    -1.36
     perfekte
    -1.33
     ideen
    -1.30
    ğına
    -1.30
    larınız
    -1.29
    cestors
    -1.29
     pogod
    -1.25
    📼
    -1.24
     conclusione
    -1.23
    POSITIVE LOGITS
     is
    2.22
     a
    1.78
     Contrary
    1.50
     overwhelmingly
    1.41
     was
    1.38
    upyter
    1.38
     zeichnet
    1.35
     has
    1.34
     Because
    1.34
     which
    1.34
    Activations Density 0.142%

    No Known Activations