© 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. 14901
    Prev
    Next
    INDEX
    Explanations

    Flex followed by specific terms

    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
    籏
    -3.39
    瓩
    -2.67
    魨
    -2.67
    琑
    -2.52
    屨
    -2.47
    ᨈ
    -2.44
    で大
    -2.42
    𖤍
    -2.41
    ない
    -2.36
     Introducción
    -2.34
    POSITIVE LOGITS
    的时候
    3.03
    If
    2.73
     और
    2.59
    You
    2.48
    6
    2.41
    を
    2.27
     и
    2.25
    でしたが
    2.23
    5
    2.23
     моя
    2.20
    Activations Density 0.011%

    No Known Activations