© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 104481
    Prev
    Next
    INDEX
    Explanations

    animal farm

    np_acts-logits-general · gemini-2.5-flash-lite

    Orwellian political allegory and animal fables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yun
    0.40
     namik
    0.39
    蔭
    0.39
     strongest
    0.39
     Nam
    0.38
     sens
    0.38
     Vân
    0.38
     Mojave
    0.38
     canyons
    0.37
     云
    0.37
    POSITIVE LOGITS
     एनिमल
    0.56
     Orwell
    0.55
     Veterinary
    0.52
    Animal
    0.52
     Animal
    0.50
     Livestock
    0.48
    🐷
    0.47
     veterinary
    0.46
     Animals
    0.45
     동물
    0.45
    Activations Density 0.009%

    No Known Activations