© 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. 55871
    Prev
    Next
    INDEX
    Explanations

    expert in a subject or role

    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
    و
    0.91
    ни
    0.82
    IVI
    0.72
     Всё
    0.71
    ت
    0.70
     делает
    0.70
    НИЕ
    0.70
    기
    0.69
    এম
    0.68
    j
    0.68
    POSITIVE LOGITS
     in
    1.09
    in
    0.90
    7
    0.83
     on
    0.81
    8
    0.80
    0
    0.75
    2
    0.75
     roundtable
    0.72
    line
    0.64
    sim
    0.62
    Activations Density 0.013%

    No Known Activations