© 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. 47253
    Prev
    Next
    INDEX
    Explanations

    repetitive sequences and fantasy

    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
     إذا
    0.56
     เขา
    0.53
     สม
    0.50
     نيك
    0.49
    除此之外
    0.48
     ৃ
    0.46
    เข
    0.45
     enregist
    0.45
     فهر
    0.45
     देऊ
    0.45
    POSITIVE LOGITS
    {}",
    0.51
     culminating
    0.43
    様な
    0.41
    })$,
    0.38
    散
    0.38
    க
    0.38
    {{
    0.37
    {
    0.37
     arth
    0.37
    [
    0.36
    Activations Density 0.002%

    No Known Activations