© 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. 22-GEMMASCOPE-RES-131K
    7. 26055
    Prev
    Next
    INDEX
    Explanations

    by innovative means

    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
    撄
    -1.27
     dekoratif
    -1.23
    twenty
    -1.16
    sistence
    -1.16
    čnost
    -1.14
    junctive
    -1.11
     patrie
    -1.06
    consola
    -1.05
     Sociale
    -1.05
     jepang
    -1.05
    POSITIVE LOGITS
     sogenannte
    1.15
     continuamente
    1.13
     allmäh
    1.09
     erheblich
    1.08
     постепенно
    1.06
     ‘‘
    1.05
     using
    1.05
     препарат
    1.05
    телем
    1.02
    يلات
    1.02
    Activations Density 0.169%

    No Known Activations