© 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. 43395
    Prev
    Next
    INDEX
    Explanations

    help us improve

    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
    baus
    -1.38
     griega
    -1.31
     vaše
    -1.29
    ドゥ
    -1.27
    名为
    -1.27
    reiben
    -1.22
     pierwszym
    -1.20
    ﻂ
    -1.19
    ଼
    -1.19
     első
    -1.18
    POSITIVE LOGITS
    licted
    1.48
     view
    1.47
    en
    1.46
    ly
    1.34
     разных
    1.27
    s
    1.25
    "+
    1.23
     now
    1.23
    ellement
    1.20
    ("
    1.20
    Activations Density 0.022%

    No Known Activations