© 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. 15492
    Prev
    Next
    INDEX
    Explanations

    describing appearance and contrast

    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
    cuits
    -1.03
     também
    -0.99
    understanding
    -0.97
     modificar
    -0.96
     vám
    -0.96
    openhagen
    -0.94
    смотр
    -0.94
    ΐ
    -0.94
     Nội
    -0.94
    kunft
    -0.94
    POSITIVE LOGITS
     contrast
    1.16
     contrasts
    1.14
     stark
    1.13
     looks
    1.05
     look
    1.04
     contrasting
    1.02
     looked
    1.02
    contrast
    0.99
    Against
    0.96
     highlighting
    0.92
    Activations Density 0.045%

    No Known Activations