© 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. 53780
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT * FROM

    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
    >
    1.01
    <0x80>
    0.91
    ل
    0.78
    *
    0.77
    기
    0.75
    ból
    0.70
    ors
    0.69
    나
    0.68
    anın
    0.67
    olí
    0.67
    POSITIVE LOGITS
    tem
    0.64
     for
    0.63
     in
    0.62
    tim
    0.54
    //*
    0.53
     }^{*}
    0.51
    dann
    0.51
     Stars
    0.50
     Chaplain
    0.50
    ua
    0.49
    Activations Density 0.098%

    No Known Activations