© 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. 74779
    Prev
    Next
    INDEX
    Explanations

    data storage and code

    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
     just
    -1.67
     at
    -1.61
    。『
    -1.48
     one
    -1.45
     -
    -1.45
    :
    -1.44
     still
    -1.41
     will
    -1.41
    7
    -1.39
     after
    -1.38
    POSITIVE LOGITS
     OTHER
    1.52
    虓
    1.36
     吴
    1.36
    我们
    1.34
     帅气
    1.30
     DIFFERENT
    1.30
     három
    1.29
     emm
    1.27
     créer
    1.27
    jourd
    1.27
    Activations Density 0.432%

    No Known Activations