© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 50040
    Prev
    Next
    INDEX
    Explanations

    definitions and scientific terms

    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
    nath
    0.51
    tree
    0.49
    ená
    0.48
    g
    0.46
    az
    0.45
    真相
    0.43
    巫
    0.42
     robbed
    0.42
    en
    0.42
    etan
    0.42
    POSITIVE LOGITS
     į
    0.52
    Õ
    0.51
     교육
    0.50
    Parrocchia
    0.49
     지역
    0.49
     יד
    0.48
     было
    0.48
     участок
    0.48
     груп
    0.46
     הה
    0.46
    Activations Density 0.025%

    No Known Activations