© 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. 64277
    Prev
    Next
    INDEX
    Explanations

    miniature scenes

    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
     statue
    -0.86
     примі
    -0.86
    上涨
    -0.81
    žd
    -0.77
     ISNI
    -0.75
     museo
    -0.74
     которыми
    -0.72
     antibody
    -0.71
     Genome
    -0.70
    kser
    -0.70
    POSITIVE LOGITS
     miniature
    1.64
     scene
    1.58
     scenes
    1.52
    miniature
    1.36
     houses
    1.30
     Miniature
    1.24
     scenery
    1.22
    dior
    1.21
    scene
    1.20
     miniatures
    1.19
    Activations Density 0.025%

    No Known Activations