© 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. 73391
    Prev
    Next
    INDEX
    Explanations

    code for combining data

    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
     &
    -1.69
     vagy
    -1.54
    หรือ
    -1.53
    又は
    -1.52
    または
    -1.48
     или
    -1.46
     следу
    -1.45
    落ちる
    -1.45
    ly
    -1.44
    our
    -1.37
    POSITIVE LOGITS
    ：……
    1.49
    钲
    1.48
    śmy
    1.43
    irii
    1.42
     juf
    1.40
    jadikan
    1.40
    ...")
    1.39
    шую
    1.39
    ötzlich
    1.38
    merkungen
    1.38
    Activations Density 0.005%

    No Known Activations