© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6232
    Prev
    Next
    INDEX
    Explanations

    LMSYS, CMS, ms, ys

    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
     ValueError
    0.48
    skap
    0.47
     Testament
    0.46
    ’
    0.46
     الحال
    0.45
    吼
    0.44
     XRP
    0.43
     dele
    0.43
     Fokus
    0.42
    of
    0.42
    POSITIVE LOGITS
    IS
    0.55
    د
    0.52
     siglas
    0.51
    RMS
    0.50
     RMS
    0.49
     системы
    0.49
    건
    0.46
    BFS
    0.45
     TMS
    0.45
    एस
    0.45
    Activations Density 0.026%

    No Known Activations