© 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. 58070
    Prev
    Next
    INDEX
    Explanations

    dinosaur and Jurassic Park

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

    dinosaurs

    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
    ട്ട്
    0.48
     smlou
    0.47
    坵
    0.45
    溏
    0.44
     शायरी
    0.43
    Ꮞ
    0.42
     यूनिवर्सल
    0.42
    醮
    0.42
     disinvestment
    0.42
    řen
    0.42
    POSITIVE LOGITS
     dinosaur
    1.10
     Jurassic
    1.05
     dinosaurs
    1.02
     dino
    0.99
     Cretaceous
    0.97
     Dinosaur
    0.95
    Jurassic
    0.91
     paleont
    0.89
     fossil
    0.88
     Dino
    0.85
    Activations Density 0.025%

    No Known Activations