© 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. 112499
    Prev
    Next
    INDEX
    Explanations

    closing information or external links

    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
     schlug
    -1.27
    ri
    -1.27
     my
    -1.22
    l
    -1.20
     hned
    -1.19
     kunnen
    -1.19
     pictured
    -1.19
     sprechen
    -1.17
     myth
    -1.16
     който
    -1.16
    POSITIVE LOGITS
    if
    1.73
    etted
    1.54
    ”،
    1.48
    ítése
    1.48
    ulfon
    1.48
    thral
    1.45
    KEYCODE
    1.41
    ophageal
    1.41
    racked
    1.40
    titial
    1.38
    Activations Density 0.050%

    No Known Activations