© 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-262K
    7. 34607
    Prev
    Next
    INDEX
    Explanations

    country, legal, political, development

    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_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
    通り
    0.46
    ف
    0.43
    вши
    0.42
     ре
    0.42
    мець
    0.41
    ח
    0.41
    か
    0.41
    深
    0.40
    ند
    0.39
    。
    0.39
    POSITIVE LOGITS
     Flugh
    0.54
     myriad
    0.53
     blowout
    0.53
     broch
    0.51
     swimmers
    0.51
     blower
    0.48
     semicircle
    0.48
    pist
    0.47
     variant
    0.46
     pilgrimage
    0.46
    Activations Density 0.001%

    No Known Activations