© 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. 40-GEMMASCOPE-2-RES-262K
    7. 99992
    Prev
    Next
    INDEX
    Explanations

    Sticker, Festival, Award, Metal, docking

    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_40_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
    aparikkh
    0.38
    eliac
    0.38
    怏
    0.38
    [multimodal]
    0.37
    rektor
    0.37
     репре
    0.36
     மய
    0.36
    以后
    0.36
     ويع
    0.35
    ٺ
    0.35
    POSITIVE LOGITS
     Sticker
    0.43
     Festival
    0.42
     Award
    0.40
    İY
    0.40
     Adds
    0.39
     灯
    0.39
     Metal
    0.38
     docking
    0.38
     Aqua
    0.38
    variants
    0.38
    Activations Density 0.000%

    No Known Activations