© 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. 42923
    Prev
    Next
    INDEX
    Explanations

    film comedians

    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
     Island
    0.70
    ጨም
    0.68
     Ix
    0.65
     Grief
    0.62
     If
    0.61
    ar
    0.60
     Trees
    0.60
    㤈
    0.60
    㤟
    0.58
     U
    0.57
    POSITIVE LOGITS
    ोज
    0.62
    Figura
    0.62
    خ
    0.61
    ین
    0.60
     від
    0.60
     indiquant
    0.58
    تها
    0.55
     washable
    0.54
    took
    0.53
    ة
    0.53
    Activations Density 0.000%

    No Known Activations