© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12933
    Prev
    Next
    INDEX
    Explanations

    cabal takedown, Doctor from, timekeeping

    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
     ancora
    -1.41
     you
    -1.40
     هذه
    -1.33
    новения
    -1.31
    剖
    -1.28
    beca
    -1.27
    LINUX
    -1.27
     use
    -1.24
    𝄆
    -1.23
     kter
    -1.23
    POSITIVE LOGITS
    ">
    1.48
     =
    1.48
    にほんブログ村
    1.47
    r
    1.39
    نکته
    1.39
    与此同时
    1.35
    توضی
    1.34
     and
    1.34
    8
    1.30
     pribadi
    1.27
    Activations Density 0.133%

    No Known Activations