© 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. 102019
    Prev
    Next
    INDEX
    Explanations

    m2

    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
    }
    -2.63
     był
    -2.47
    有
    -2.42
    是
    -2.28
     and
    -2.19
    coledì
    -2.11
     gekomen
    -2.09
    ﺒ
    -2.08
    大部分
    -2.08
     možné
    -2.03
    POSITIVE LOGITS
    嵛
    2.92
    vantaged
    2.38
    骘
    2.33
    鹪
    2.25
    衕
    2.23
     Для
    2.22
    ਃ
    2.22
    頫
    2.19
    笵
    2.14
    臜
    2.14
    Activations Density 0.035%

    No Known Activations