© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 33945
    Prev
    Next
    INDEX
    Explanations

    array, functions, and lovebirds

    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
    ו
    0.66
     archbishop
    0.64
    Ữ
    0.62
     simplify
    0.57
     feedbacks
    0.56
    λούν
    0.56
    lices
    0.55
    lN
    0.55
     kullanımı
    0.55
    世界の
    0.55
    POSITIVE LOGITS
    াত্র
    0.53
    ة
    0.53
     ห
    0.52
    ی
    0.49
     ش
    0.48
     حج
    0.48
     Battles
    0.47
    chronic
    0.47
    یی
    0.47
     Mathew
    0.46
    Activations Density 0.000%

    No Known Activations