© 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. 66459
    Prev
    Next
    INDEX
    Explanations

    common phrases or idioms

    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
    !!!!!!!
    -1.36
    !!!!!!
    -1.33
     juſ
    -1.30
    ctos
    -1.25
     heilig
    -1.23
     trener
    -1.21
     spektak
    -1.19
    こういった
    -1.18
     reclamo
    -1.17
    傒
    -1.17
    POSITIVE LOGITS
     provide
    1.23
     atlik
    1.14
    呐
    1.13
     puts
    1.09
    出版年
    1.06
    mAuth
    1.05
     fase
    1.02
    un
    1.02
    иму
    1.02
     tries
    1.02
    Activations Density 0.041%

    No Known Activations