© 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. 63407
    Prev
    Next
    INDEX
    Explanations

    image sizes

    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
     garan
    -0.94
     amplit
    -0.85
    chrän
    -0.84
    ラメ
    -0.83
    ients
    -0.83
     galaxia
    -0.82
     пари
    -0.82
    iat
    -0.82
     cabra
    -0.81
    irements
    -0.81
    POSITIVE LOGITS
     type
    1.10
     image
    0.96
     sizes
    0.94
     images
    0.78
     boil
    0.75
    ofition
    0.74
     masks
    0.68
    营
    0.68
     堂
    0.68
    setImage
    0.68
    Activations Density 0.011%

    No Known Activations