© 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. 67861
    Prev
    Next
    INDEX
    Explanations

    It is

    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
     inside
    -1.55
     on
    -1.54
     Mitteln
    -1.52
    cheerful
    -1.51
    翳
    -1.50
     then
    -1.50
    ୪
    -1.43
     daarvoor
    -1.39
     CONTRIBUTOR
    -1.37
     at
    -1.36
    POSITIVE LOGITS
    1
    2.45
    0
    1.84
    3
    1.70
    9
    1.68
    8
    1.63
    2
    1.54
    After
    1.52
    4
    1.51
    5
    1.49
     “
    1.48
    Activations Density 0.152%

    No Known Activations