© 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. 52840
    Prev
    Next
    INDEX
    Explanations

    send specific

    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
     selling
    0.44
    '
    0.44
    術
    0.41
     miei
    0.41
     adam
    0.40
    裾
    0.40
    ᑎ
    0.39
     leaned
    0.38
     Leib
    0.38
     Gottes
    0.38
    POSITIVE LOGITS
    اج
    0.45
    的速度
    0.45
    app
    0.44
     Detention
    0.43
     প্রতিক্রি
    0.43
    粽
    0.42
     Rxe
    0.41
    ੍ਰ
    0.41
    使用的是
    0.41
    yl
    0.41
    Activations Density 0.001%

    No Known Activations