© 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. 881
    Prev
    Next
    INDEX
    Explanations

    player status and availability

    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
     of
    -1.63
    ַת
    -1.38
     sogar
    -1.30
     Мексика
    -1.30
    </em>
    -1.28
    )
    -1.20
    </h5>
    -1.18
     Кер
    -1.17
     otorga
    -1.16
     otras
    -1.16
    POSITIVE LOGITS
    which
    1.36
     for
    1.35
    会有
    1.34
    ﻃ
    1.34
     will
    1.31
    mặt
    1.30
     для
    1.29
     Traducción
    1.25
    estones
    1.23
    sió
    1.21
    Activations Density 0.023%

    No Known Activations