© 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. 34-GEMMASCOPE-RES-131K
    7. 107888
    Prev
    Next
    INDEX
    Explanations

    image composition and manipulation

    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_34/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
    estrian
    -0.73
    strument
    -0.73
     impulso
    -0.72
    を表
    -0.72
    スル
    -0.72
    ressional
    -0.71
    tôi
    -0.70
    ありますか
    -0.69
    Nhà
    -0.69
    acruz
    -0.68
    POSITIVE LOGITS
     composit
    1.73
     composite
    1.52
    composite
    1.36
     composites
    1.34
    Composite
    1.34
     Composite
    1.26
    合成
    1.20
     compositor
    1.16
    Matte
    1.10
    composites
    1.07
    Activations Density 0.030%

    No Known Activations