© 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. 7598
    Prev
    Next
    INDEX
    Explanations

    people groups

    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
     zarówno
    -1.33
     itself
    -1.28
     has
    -1.27
    ')
    -1.27
    ())
    -1.25
    ąp
    -1.24
    pios
    -1.24
     is
    -1.22
    冪
    -1.21
    +}
    -1.19
    POSITIVE LOGITS
     themselves
    1.80
    geſ
    1.50
    cần
    1.33
     ľah
    1.30
     actuaciones
    1.30
     keď
    1.29
    そろ
    1.29
     炒め
    1.27
     who
    1.26
    kệ
    1.26
    Activations Density 0.104%

    No Known Activations