© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39715
    Prev
    Next
    INDEX
    Explanations

    reading status or code comments

    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
    The
    -2.28
    ۹
    -2.23
    ～～
    -2.22
    \
    -2.22
    甦
    -2.20
    They
    -2.19
     vielleicht
    -2.19
    ية
    -2.19
    ﮟ
    -2.09
     he
    -2.08
    POSITIVE LOGITS
    婬
    2.41
    ghalaya
    2.39
    蚡
    2.36
    慊
    2.19
    玙
    2.16
    肫
    2.16
    鯪
    2.11
    骘
    2.08
     pembayaran
    2.06
    ⛛
    2.06
    Activations Density 0.000%

    No Known Activations