© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80846
    Prev
    Next
    INDEX
    Explanations

    creating, processing, or transforming

    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
    {
    -1.53
     you
    -1.50
    S
    -1.36
    特别是
    -1.35
    when
    -1.35
     impon
    -1.27
    R
    -1.25
    ‘‘
    -1.23
     beim
    -1.23
     cristian
    -1.22
    POSITIVE LOGITS
     for
    1.73
     into
    1.70
    homonymie
    1.52
    derdag
    1.45
     a
    1.30
     összefoglaló
    1.29
    ฎ
    1.27
     stratég
    1.25
     különböző
    1.25
     kérdés
    1.24
    Activations Density 0.143%

    No Known Activations