© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49182
    Prev
    Next
    INDEX
    Explanations

    ducks and mallards

    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_16_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
     l
    0.94
    ?
    0.93
     will
    0.84
    I
    0.79
    e
    0.79
    !
    0.78
     el
    0.78
     wouldn
    0.75
     can
    0.75
    a
    0.71
    POSITIVE LOGITS
    हून
    0.80
    ми
    0.80
     ducks
    0.74
    жном
    0.73
    плы
    0.71
    滯
    0.71
    loon
    0.70
    یم
    0.69
     Ducks
    0.69
    اني
    0.67
    Activations Density 0.006%

    No Known Activations