© 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. 14977
    Prev
    Next
    INDEX
    Explanations

    quoted speech

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

    This neuron activates on numeric tokens, highlighting numbers and numerical expressions 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
     what
    -1.75
     that
    -1.61
     their
    -1.34
     any
    -1.32
     those
    -1.31
     had
    -1.31
     if
    -1.31
     which
    -1.30
    Tomasz
    -1.30
     on
    -1.29
    POSITIVE LOGITS
    だけです
    1.70
    ROGEN
    1.59
    PhysRevD
    1.44
    heater
    1.38
     beide
    1.31
     メニュー
    1.30
     appla
    1.30
    agonal
    1.30
    眼里
    1.28
    将他
    1.28
    Activations Density 0.018%

    No Known Activations