© 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. 53-GEMMASCOPE-2-RES-262K
    7. 49705
    Prev
    Next
    INDEX
    Explanations

    celebration and foreign scripts

    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_53_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
     சி
    0.41
    niejszych
    0.40
     Donnie
    0.40
     tù
    0.39
    ומי
    0.39
    व
    0.39
     दि
    0.38
    ♥️
    0.37
    ಮಿ
    0.36
    Giovanni
    0.36
    POSITIVE LOGITS
    鹘
    0.46
     fame
    0.45
    esen
    0.45
     excited
    0.43
     celebr
    0.43
    스가
    0.42
     fuse
    0.41
    fus
    0.41
    טא
    0.41
     fus
    0.40
    Activations Density 0.000%

    No Known Activations