© 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. 22-GEMMASCOPE-RES-131K
    7. 14926
    Prev
    Next
    INDEX
    Explanations

    list element separators

    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_22/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
     coreano
    -1.27
     francisco
    -1.25
     kompati
    -1.21
     antonio
    -1.20
     marta
    -1.20
     but
    -1.19
    ileen
    -1.16
     Ferdinando
    -1.15
     sista
    -1.14
    yesha
    -1.14
    POSITIVE LOGITS
    <bos>
    1.16
     conceito
    1.11
    .....
    1.11
    .........
    1.09
    そして
    1.09
     actitudes
    1.08
    ............
    1.06
     nuevamente
    1.06
     ocul
    1.04
     ......
    1.03
    Activations Density 0.048%

    No Known Activations