© 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. 44718
    Prev
    Next
    INDEX
    Explanations

    XXVIII

    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
     dynamis
    -1.27
     liberi
    -1.26
    </blockquote>
    -1.26
     baie
    -1.24
    taki
    -1.23
    hauled
    -1.22
     akumulator
    -1.21
     metus
    -1.20
     originali
    -1.18
    蟶
    -1.17
    POSITIVE LOGITS
     only
    1.50
    lanır
    1.47
     зді
    1.26
     Unterschied
    1.25
     violencia
    1.24
    局面
    1.24
    途中
    1.23
     know
    1.23
     zlep
    1.23
    Only
    1.21
    Activations Density 0.013%

    No Known Activations