© 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. 84036
    Prev
    Next
    INDEX
    Explanations

    bytecode and virtual machines

    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
     莉
    -1.55
     or
    -1.53
     Ciebie
    -1.49
     pilares
    -1.47
    外し
    -1.46
    有两
    -1.45
    ());
    -1.45
    擁有
    -1.40
     obtenidos
    -1.40
     perdido
    -1.39
    POSITIVE LOGITS
     there
    1.54
     into
    1.40
     aparecen
    1.30
    FECT
    1.29
    ouac
    1.28
    渺
    1.25
    瞄
    1.25
     culturale
    1.24
    月亮
    1.23
     its
    1.23
    Activations Density 0.082%

    No Known Activations