© 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. 101076
    Prev
    Next
    INDEX
    Explanations

    rates per second

    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
    ጵ
    -1.63
     valioso
    -1.58
    踞
    -1.55
     deudas
    -1.52
     establecido
    -1.49
     cometido
    -1.49
    ៌
    -1.48
    *),
    -1.46
     estímulo
    -1.45
     rugged
    -1.44
    POSITIVE LOGITS
     The
    1.88
     "
    1.45
     (
    1.39
    ("
    1.37
    ="
    1.35
     '
    1.34
     /
    1.30
    в
    1.28
     luch
    1.28
     ">
    1.27
    Activations Density 0.015%

    No Known Activations