© 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. 60095
    Prev
    Next
    INDEX
    Explanations

    durations of time

    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
    aussian
    -1.53
    elte
    -1.48
    ITÉ
    -1.45
    ("");
    -1.39
     دشمن
    -1.35
    "…
    -1.35
    Answered
    -1.33
    critti
    -1.33
     للبيع
    -1.32
    ÊNCIA
    -1.32
    POSITIVE LOGITS
    .
    1.43
     Either
    1.24
     my
    1.23
     like
    1.22
     advise
    1.16
     overall
    1.14
     our
    1.13
     either
    1.13
     Fonction
    1.11
     gần
    1.10
    Activations Density 0.096%

    No Known Activations