© 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. 34125
    Prev
    Next
    INDEX
    Explanations

    programming constructs and documentation

    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
     their
    -1.48
     a
    -1.41
     like
    -1.37
    /*!
    -1.35
     his
    -1.30
    //!
    -1.27
    七十
    -1.21
     natür
    -1.20
     about
    -1.14
     großer
    -1.11
    POSITIVE LOGITS
     despues
    1.30
    极其
    1.28
     porcent
    1.26
     döner
    1.24
    ,
    1.23
     торт
    1.22
    Recept
    1.20
     thous
    1.19
    Leopard
    1.18
    ormais
    1.16
    Activations Density 0.002%

    No Known Activations