© 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. 65393
    Prev
    Next
    INDEX
    Explanations

    performing musicians

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

    The neuron activates on numeric tokens—years, measurements, and other numbers (including 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_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
     our
    -2.08
     this
    -1.47
     we
    -1.34
    %)$
    -1.27
     today
    -1.26
     what
    -1.20
     lengan
    -1.19
     these
    -1.18
    するので
    -1.13
    ciri
    -1.11
    POSITIVE LOGITS
    atized
    1.28
    termilk
    1.26
    atization
    1.24
    stes
    1.23
    ropic
    1.18
    謚
    1.17
    下来的
    1.16
    ヴァ
    1.16
     tente
    1.16
     revel
    1.15
    Activations Density 0.035%

    No Known Activations