© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 13308
    Prev
    Next
    INDEX
    Explanations

    HTTP Error

    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
    SOCK
    0.43
     вяза
    0.38
    ABOR
    0.37
    兵
    0.37
    鍮
    0.37
    全局
    0.35
    锁
    0.35
    Chen
    0.35
    婵
    0.35
    泛
    0.34
    POSITIVE LOGITS
     cub
    0.82
     Cub
    0.66
    Cub
    0.64
    cub
    0.63
     walk
    0.60
     mixer
    0.58
     Mira
    0.56
    Walk
    0.56
     Walk
    0.55
     quadrant
    0.54
    Activations Density 0.003%

    No Known Activations