© 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. 20836
    Prev
    Next
    INDEX
    Explanations

    the company

    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
     списка
    -1.45
    Morfologia
    -1.38
     känna
    -1.36
    ↵↵
    -1.35
     including
    -1.34
    från
    -1.32
    nipeg
    -1.31
     with
    -1.30
    這些
    -1.29
     those
    -1.27
    POSITIVE LOGITS
     his
    1.92
     would
    1.67
     to
    1.64
     its
    1.45
     part
    1.40
    _
    1.40
     wanted
    1.36
     несмотря
    1.34
     “
    1.33
     only
    1.30
    Activations Density 0.070%

    No Known Activations