© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14104
    Prev
    Next
    INDEX
    Explanations

    URLs with query parameters

    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
     prípade
    -1.69
     trabajó
    -1.57
     primeiros
    -1.52
    ۠
    -1.51
    ネットで
    -1.51
     tomto
    -1.47
    というわけで
    -1.46
    ).
    -1.45
    ܔ
    -1.44
    僕は
    -1.43
    POSITIVE LOGITS
    </h3>
    1.70
     of
    1.62
    咐
    1.38
    ïdes
    1.38
     her
    1.34
    ᴋ
    1.33
    </i>
    1.32
     годом
    1.31
    гляд
    1.30
     (
    1.29
    Activations Density 0.002%

    No Known Activations