© 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. 16-GEMMASCOPE-2-RES-262K
    7. 28874
    Prev
    Next
    INDEX
    Explanations

    `of Wei`

    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
    ین
    0.73
    ۰
    0.71
    defined
    0.69
    Y
    0.67
    omit
    0.64
    asm
    0.62
    escaping
    0.62
    forestation
    0.61
    ቛ
    0.61
    advantages
    0.61
    POSITIVE LOGITS
    ;
    0.76
    },
    0.71
     ממ
    0.68
    是用
    0.66
    રા
    0.65
     bashing
    0.65
     extravaganza
    0.65
    t
    0.64
    ",
    0.63
    璿
    0.63
    Activations Density 0.000%

    No Known Activations