© 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. 53995
    Prev
    Next
    INDEX
    Explanations

    appreciate, exhilaration, crave, layering, temporada alta, impact factor

    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
    kt
    0.46
    uri
    0.42
    \
    0.41
    thumbnail
    0.41
    alt
    0.40
    iken
    0.40
     rie
    0.39
     vallée
    0.39
    $%
    0.39
    oi
    0.38
    POSITIVE LOGITS
     Евге
    0.52
     නිෂ්
    0.51
     Ша
    0.50
    เล็ก
    0.47
     መጨ
    0.46
    FirstFit
    0.46
    এসসি
    0.46
    जेक्शन
    0.46
     Shao
    0.46
    𝘧
    0.45
    Activations Density 0.011%

    No Known Activations