© 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. 26707
    Prev
    Next
    INDEX
    Explanations

    HTML, programming, data, text

    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
     kompati
    -1.20
    ämie
    -1.14
     Traducción
    -1.09
    皤
    -1.09
     reizen
    -1.09
     dát
    -1.07
    lampe
    -1.05
     stratég
    -1.05
     Envío
    -1.05
    珠宝
    -1.03
    POSITIVE LOGITS
     not
    1.28
     where
    1.20
     helps
    1.06
     includes
    1.05
    ties
    1.05
     always
    1.02
     ….
    1.02
     just
    1.02
     how
    1.01
     group
    1.01
    Activations Density 0.001%

    No Known Activations