© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54989
    Prev
    Next
    INDEX
    Explanations

    emojis and punctuation

    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
     IN
    0.51
     ON
    0.47
     וב
    0.46
     実
    0.45
     AND
    0.45
     מת
    0.43
     orient
    0.43
     המת
    0.43
    ժ
    0.42
     for
    0.42
    POSITIVE LOGITS
    تك
    0.51
    columnwidth
    0.47
     belted
    0.46
     saludable
    0.46
     मुख्‍य
    0.44
    jsdelivr
    0.44
    bleed
    0.44
    𐰴
    0.43
    PKG
    0.43
    اد
    0.42
    Activations Density 0.008%

    No Known Activations