© 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. 20051
    Prev
    Next
    INDEX
    Explanations

    programming and names

    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
     from
    -1.65
     your
    -1.47
     of
    -1.34
     auparavant
    -1.26
     rito
    -1.24
    aujourd
    -1.20
    ώ
    -1.17
    ゜
    -1.16
     vielleicht
    -1.13
    OTHER
    -1.11
    POSITIVE LOGITS
     HttpNotFound
    1.46
    之后
    1.38
    itemize
    1.37
    说过
    1.29
    มี
    1.29
    𝑧
    1.28
    **/
    1.27
    "،
    1.24
    ́s
    1.24
     turysty
    1.23
    Activations Density 0.000%

    No Known Activations