© 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. 77763
    Prev
    Next
    INDEX
    Explanations

    Shrek characters and movie production

    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
     Prey
    -0.85
     CAV
    -0.81
    Spectrum
    -0.73
     Pilot
    -0.73
    尊重
    -0.73
     sigma
    -0.70
     assistance
    -0.70
     gam
    -0.69
    зей
    -0.69
     Spectrum
    -0.69
    POSITIVE LOGITS
     Shrek
    1.42
    Shrek
    1.12
     ogre
    1.09
     Donkey
    0.93
     Fiona
    0.82
    ogre
    0.80
    Donkey
    0.77
     eloku
    0.77
     Greenberg
    0.75
     Ogre
    0.75
    Activations Density 0.016%

    No Known Activations