© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13825
    Prev
    Next
    INDEX
    Explanations

    bird

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

    bird species

    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_16k_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
     werewolf
    0.56
    犬
    0.54
    🐂
    0.54
     cave
    0.52
    🦈
    0.52
     牛
    0.50
    熊本
    0.50
     sharks
    0.49
     shark
    0.48
    🐶
    0.48
    POSITIVE LOGITS
     bird
    1.48
     birds
    1.38
     plumage
    1.32
     Bird
    1.30
     Birds
    1.28
     пти
    1.26
     avian
    1.24
     feathers
    1.22
    鳥
    1.22
    Bird
    1.20
    Activations Density 0.335%

    No Known Activations