© 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. 21191
    Prev
    Next
    INDEX
    Explanations

    content value attributes

    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
    r
    -1.67
     rique
    -1.66
    n
    -1.46
    id
    -1.43
     virtudes
    -1.43
     применение
    -1.42
     enhancing
    -1.42
     with
    -1.41
     tardes
    -1.41
    </h4>
    -1.38
    POSITIVE LOGITS
     GOtt
    1.63
     débuts
    1.52
     メニュー
    1.51
    
    1.45
     messe
    1.44
     Turquía
    1.44
    seamnă
    1.43
     ――
    1.41
     bukanlah
    1.40
     provar
    1.39
    Activations Density 0.015%

    No Known Activations