© 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. 21140
    Prev
    Next
    INDEX
    Explanations

    exercise types

    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
     there
    -1.70
     it
    -1.41
     that
    -1.25
    ៹
    -1.23
     dermed
    -1.22
    这一点
    -1.20
    っており
    -1.19
     débat
    -1.16
    そこは
    -1.15
     hubo
    -1.13
    POSITIVE LOGITS
    Exeunt
    1.41
     következő
    1.26
    ispiele
    1.20
     Ведь
    1.18
    einer
    1.16
     növény
    1.14
     neko
    1.13
     października
    1.13
    eket
    1.13
    <tr>
    1.12
    Activations Density 0.021%

    No Known Activations