© 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. 57833
    Prev
    Next
    INDEX
    Explanations

    images

    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
     festa
    -0.78
     masculin
    -0.76
    сна
    -0.74
    pakatan
    -0.74
    無料
    -0.73
     Navarro
    -0.73
     flit
    -0.73
    èrement
    -0.72
    ifié
    -0.72
     TOC
    -0.71
    POSITIVE LOGITS
     images
    1.49
     Images
    1.23
    images
    1.22
     image
    1.16
     imágenes
    1.15
     safe
    1.04
    Images
    1.01
     IMAGES
    1.01
     Safe
    0.96
    imagens
    0.91
    Activations Density 0.032%

    No Known Activations