© 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. 8220
    Prev
    Next
    INDEX
    Explanations

    status, because, indeed

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

    The neuron activates on numerical tokens (e.g. section numbers, decimal values, figures).

    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
    Leírás
    -1.58
    gambarkan
    -1.53
     券
    -1.49
    Suche
    -1.44
    توضیحات
    -1.42
    sarung
    -1.42
    ᨈ
    -1.39
    Hvordan
    -1.38
     bättre
    -1.34
    Kindle
    -1.33
    POSITIVE LOGITS
     their
    1.95
     then
    1.85
     in
    1.75
     the
    1.52
     time
    1.44
    useNewUrlParser
    1.43
    ).'
    1.41
     we
    1.38
    >${
    1.38
    elementAt
    1.35
    Activations Density 0.283%

    No Known Activations