© 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. 128525
    Prev
    Next
    INDEX
    Explanations

    actions of research and development

    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
     to
    -1.49
     with
    -1.41
     for
    -1.32
     from
    -1.27
     «
    -0.88
     –
    -0.85
    ورات
    -0.84
     її
    -0.83
     which
    -0.83
    leyebilirsiniz
    -0.82
    POSITIVE LOGITS
     entornos
    1.22
     możesz
    1.14
     aparatos
    1.10
     erhi
    1.09
     faudrait
    1.06
     camiones
    1.06
    couldn
    1.05
     coreano
    1.04
     contenedores
    1.03
     bolsillos
    1.02
    Activations Density 0.169%

    No Known Activations