© 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. 10-GEMMASCOPE-RES-131K
    7. 22270
    Prev
    Next
    INDEX
    Explanations

    energy studies

    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_10/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
     other
    -1.56
     his
    -1.55
     as
    -1.48
     people
    -1.42
     njego
    -1.41
     our
    -1.37
    他に
    -1.36
     few
    -1.33
     about
    -1.32
     the
    -1.30
    POSITIVE LOGITS
    pography
    1.34
    encies
    1.30
    берг
    1.29
    urazione
    1.27
    đèn
    1.27
    ري
    1.27
    ppings
    1.27
    peka
    1.26
    ین
    1.24
    šnje
    1.24
    Activations Density 0.159%

    No Known Activations