© 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. 8106
    Prev
    Next
    INDEX
    Explanations

    javascript or python code segments

    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
     التالي
    -1.30
    medi
    -1.28
    gesetzt
    -1.25
    ten
    -1.23
    ad
    -1.23
    mised
    -1.22
     שלך
    -1.21
    mos
    -1.21
    dication
    -1.20
    ,”
    -1.18
    POSITIVE LOGITS
     what
    2.08
     some
    1.60
     it
    1.47
     how
    1.45
     so
    1.39
     nejsou
    1.38
     trying
    1.37
    に行ってきました
    1.34
     about
    1.30
     consape
    1.30
    Activations Density 0.029%

    No Known Activations