© 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-16K
    7. 13919
    Prev
    Next
    INDEX
    Explanations

    function takes arguments

    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_16k_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
     Και
    0.38
    轨迹
    0.38
    结束
    0.37
    独
    0.36
    дем
    0.36
    效应
    0.36
     permisos
    0.36
    ⎝
    0.36
    执行
    0.36
    音が
    0.36
    POSITIVE LOGITS
     cupcake
    0.43
     arguing
    0.43
     dunno
    0.42
     impure
    0.41
     _,
    0.41
     intimacy
    0.40
     ricev
    0.40
     Kappa
    0.40
     neoprene
    0.40
     gelato
    0.39
    Activations Density 0.273%

    No Known Activations