© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42071
    Prev
    Next
    INDEX
    Explanations

    rarely used

    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
     скром
    -1.27
     représenter
    -1.27
    BEFORE
    -1.25
     Шаг
    -1.23
    picable
    -1.20
     hés
    -1.17
     кровати
    -1.17
    鹟
    -1.16
     betek
    -1.16
     participer
    -1.16
    POSITIVE LOGITS
     then
    1.55
     still
    1.42
     there
    1.34
     if
    1.30
     which
    1.27
     unused
    1.24
    leta
    1.23
     Equipment
    1.22
     If
    1.21
     Use
    1.20
    Activations Density 0.075%

    No Known Activations