© 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. 119812
    Prev
    Next
    INDEX
    Explanations

    buy from

    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
    をはじめ
    -1.48
     signifie
    -1.34
    aned
    -1.30
     différents
    -1.28
    タイプの
    -1.27
     zalando
    -1.26
    튿
    -1.25
    ”
    -1.24
     uniforme
    -1.22
     autre
    -1.21
    POSITIVE LOGITS
    」,
    1.84
     був
    1.61
    ᚷ
    1.59
     These
    1.56
    évalu
    1.55
    There
    1.53
    ÇÃO
    1.52
     領
    1.51
    We
    1.50
    Кита
    1.50
    Activations Density 0.023%

    No Known Activations