Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 424
    Prev
    Next
    INDEX
    Explanations

    bird watching and houses

    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
     मुस्क
    0.44
     производителя
    0.43
     компьютер
    0.43
    %")
    0.43
    бере
    0.42
    ัติ
    0.40
     среду
    0.40
     natoque
    0.40
    REW
    0.39
    <unused71>
    0.38
    POSITIVE LOGITS
     bird
    0.99
     birds
    0.86
     plumage
    0.83
     Bird
    0.82
    鳥
    0.80
    Bird
    0.79
     feathers
    0.77
     пти
    0.77
    bird
    0.77
    鸟
    0.76
    Activations Density 0.013%

    No Known Activations