© 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. 39620
    Prev
    Next
    INDEX
    Explanations

    thank you for

    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
     확인함
    -1.82
    說
    -1.70
    ”？
    -1.70
    兩
    -1.52
     کردیم
    -1.47
     જ
    -1.45
    roffene
    -1.45
    Причины
    -1.43
     forro
    -1.43
    的核心
    -1.41
    POSITIVE LOGITS
     that
    1.78
    4
    1.56
     are
    1.54
     will
    1.52
    ми
    1.52
     
    1.51
     you
    1.46
     Wurzeln
    1.39
    9
    1.38
     your
    1.37
    Activations Density 0.017%

    No Known Activations