© 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. 43576
    Prev
    Next
    INDEX
    Explanations

    legal citations and case summaries

    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
     pauv
    -1.44
     giorgio
    -1.41
    家を
    -1.40
     pittores
    -1.39
    :
    -1.36
     ataupun
    -1.35
    伱
    -1.33
     ("
    -1.32
     of
    -1.32
     kuliner
    -1.29
    POSITIVE LOGITS
     after
    1.56
     pudieran
    1.47
     depois
    1.46
    ↵↵
    1.44
    ebab
    1.44
     eficientes
    1.39
     heuti
    1.38
     capacidades
    1.35
     ciertamente
    1.32
     verdaderamente
    1.31
    Activations Density 0.125%

    No Known Activations