© 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. 84926
    Prev
    Next
    INDEX
    Explanations

    gear and equipment

    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
    ceptable
    -1.41
    -
    -1.22
    Ако
    -1.16
    Här
    -1.15
     mxArray
    -1.12
    Terima
    -1.11
    пания
    -1.09
     last
    -1.09
     Азербай
    -1.09
    vial
    -1.05
    POSITIVE LOGITS
     a
    1.64
     ufficio
    1.31
     from
    1.31
     plazos
    1.30
    NOWLEDGE
    1.28
     tamaños
    1.27
     الحل
    1.25
    桴
    1.23
     aiuto
    1.23
    洐
    1.22
    Activations Density 0.055%

    No Known Activations