© 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. 27538
    Prev
    Next
    INDEX
    Explanations

    preparation or steps

    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
     this
    -1.68
     their
    -1.62
     new
    -1.39
     there
    -1.39
     these
    -1.36
     they
    -1.30
    וּ
    -1.26
     récente
    -1.21
     that
    -1.20
     иногда
    -1.20
    POSITIVE LOGITS
    良いです
    1.31
    epar
    1.31
    Postup
    1.29
     BioLib
    1.23
    cheque
    1.20
    eezy
    1.20
     quatre
    1.20
     cinq
    1.19
    kull
    1.15
     ativos
    1.15
    Activations Density 0.002%

    No Known Activations