© 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-262K
    7. 92464
    Prev
    Next
    INDEX
    Explanations

    Post transformation or field generation

    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
     قصد
    0.46
     x
    0.46
     glo
    0.43
     通勤
    0.41
     q
    0.41
     df
    0.41
     México
    0.41
     ث
    0.40
     знамена
    0.40
     Ξ
    0.40
    POSITIVE LOGITS
    鹧
    0.59
     łat
    0.51
     résult
    0.48
    원에서
    0.47
     régler
    0.46
    عبير
    0.46
    korzyst
    0.44
     conç
    0.43
    isierte
    0.43
    avasti
    0.43
    Activations Density 0.007%

    No Known Activations