© 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. 100231
    Prev
    Next
    INDEX
    Explanations

    in some cases

    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
     alér
    -1.51
     too
    -1.45
    说过
    -1.38
    比べて
    -1.36
     особли
    -1.29
     ventajas
    -1.27
     not
    -1.27
    𝗠
    -1.27
     acompañado
    -1.23
    していますが
    -1.23
    POSITIVE LOGITS
     and
    2.03
     which
    1.63
    ซึ่ง
    1.61
     will
    1.49
    ｢
    1.47
    ="
    1.41
     â
    1.36
     hingga
    1.35
    lekt
    1.32
    『
    1.30
    Activations Density 0.182%

    No Known Activations