© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129666
    Prev
    Next
    INDEX
    Explanations

    session, holiday, orrush times

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -1.20
    formatics
    -1.15
     protože
    -1.10
    شف
    -1.05
     cerim
    -1.05
     yöntem
    -1.05
     setelah
    -1.03
    onora
    -1.03
     know
    -1.02
     through
    -1.02
    POSITIVE LOGITS
     seguras
    1.20
     eenige
    1.11
     árboles
    1.11
     koo
    1.10
    ٬
    1.09
     infatti
    1.08
    ritus
    1.07
    っていない
    1.05
     粉色
    1.03
     corazones
    1.02
    Activations Density 0.078%

    No Known Activations