© 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. 8888
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     have
    -1.73
     who
    -1.49
     not
    -1.48
     NOT
    -1.41
    ajoz
    -1.38
     other
    -1.38
     tämän
    -1.32
     
    -1.30
     to
    -1.30
    」。
    -1.29
    POSITIVE LOGITS
     jule
    1.56
     ۲۰۱
    1.55
    翻譯
    1.49
     tille
    1.44
     واتس
    1.40
     masques
    1.38
     hakim
    1.38
    ♥♥
    1.37
     anadolu
    1.34
     hiz
    1.32
    Activations Density 0.016%

    No Known Activations