© 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. 31-GEMMASCOPE-2-RES-65K
    7. 16509
    Prev
    Next
    INDEX
    Explanations

    new variations

    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_31_width_65k_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
     খেলার
    0.47
    كز
    0.47
    드
    0.46
     탐
    0.45
     싶
    0.44
    愛
    0.44
    长时间
    0.44
     愛
    0.43
    ड
    0.42
    襄
    0.42
    POSITIVE LOGITS
     Choibalsan
    0.49
     nowych
    0.49
     nueva
    0.47
     neue
    0.47
     Nueva
    0.46
     new
    0.45
     neuen
    0.45
     nye
    0.44
     nuevos
    0.44
     نئے
    0.44
    Activations Density 0.008%

    No Known Activations