© 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. 17782
    Prev
    Next
    INDEX
    Explanations

    ratings scale

    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
    Shr
    0.41
    螫
    0.40
     sufrió
    0.40
     পরিস্থিতির
    0.39
     récupérer
    0.39
    শকার
    0.39
     längre
    0.39
    Estimation
    0.38
    饞
    0.38
    有两种
    0.38
    POSITIVE LOGITS
    lowest
    0.53
     lowest
    0.48
    最高
    0.46
     Lowest
    0.46
     youngest
    0.45
    最
    0.45
    Lowest
    0.44
     höchste
    0.44
    highest
    0.43
     nhất
    0.43
    Activations Density 0.190%

    No Known Activations