© 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. 9529
    Prev
    Next
    INDEX
    Explanations

    require from helpers

    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
     by
    -1.65
     to
    -1.56
    滹
    -1.55
     they
    -1.49
     it
    -1.49
    小弟
    -1.48
     He
    -1.42
     tecnológicos
    -1.39
    s
    -1.38
     文字
    -1.37
    POSITIVE LOGITS
    a
    1.62
     εδώ
    1.45
    缎
    1.42
    残
    1.38
     επίσης
    1.36
    värr
    1.36
     but
    1.35
    很难
    1.34
    ed
    1.34
    LOTTE
    1.33
    Activations Density 0.002%

    No Known Activations