© 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. 34591
    Prev
    Next
    INDEX
    Explanations

    caramel and desserts

    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
    at
    0.80
    !
    0.75
    ?
    0.68
    пы
    0.66
    ட்சிய
    0.66
    vent
    0.65
    ncia
    0.64
     Puget
    0.64
    fre
    0.59
     poetry
    0.59
    POSITIVE LOGITS
    뼈
    0.73
    める
    0.72
    లో
    0.72
    د
    0.72
     অ্যাকাউন্ট
    0.71
    OR
    0.70
    ]。
    0.70
    Glucose
    0.68
    ב
    0.68
    钀
    0.68
    Activations Density 0.004%

    No Known Activations