© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12014
    Prev
    Next
    INDEX
    Explanations

    birds, especially avian features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    泫
    0.52
    炆
    0.49
    👾
    0.48
    蚩
    0.48
    豬
    0.48
    🐂
    0.48
    🛋
    0.47
    돼
    0.47
     werewolf
    0.47
    🐷
    0.47
    POSITIVE LOGITS
     bird
    2.19
     birds
    2.08
     plumage
    1.91
     avian
    1.90
     feathers
    1.88
     Bird
    1.83
     пти
    1.78
     ornith
    1.77
    Bird
    1.71
     Birds
    1.70
    Activations Density 0.063%

    No Known Activations