© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111994
    Prev
    Next
    INDEX
    Explanations

    trending worldwide

    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
    </i>
    -2.52
    u
    -2.20
     ก็
    -2.19
    </h1>
    -2.16
    ka
    -2.13
    因为
    -2.08
     {
    -2.03
    纱
    -2.03
    z
    -2.02
     será
    -1.99
    POSITIVE LOGITS
    ”？
    2.56
    ଃ
    2.47
    𞤢
    2.44
    泔
    2.36
    後記
    2.34
    　↓
    2.31
    鋮
    2.28
    晅
    2.23
    TRIBUN
    2.22
    ～～
    2.16
    Activations Density 0.002%

    No Known Activations