© 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. 7736
    Prev
    Next
    INDEX
    Explanations

    comparisons and relations

    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
     it
    -2.13
    々は
    -1.38
    ),
    -1.36
    ISTRATION
    -1.35
    ٻ
    -1.30
     first
    -1.22
     Apakah
    -1.19
    他要
    -1.19
    他にも
    -1.18
     medu
    -1.17
    POSITIVE LOGITS
     hilsen
    1.37
     skog
    1.34
     referrerpolicy
    1.33
     tylko
    1.32
     hvid
    1.31
    ņi
    1.29
     ambassade
    1.24
     aspects
    1.23
     educativas
    1.23
     huden
    1.23
    Activations Density 0.189%

    No Known Activations