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

    Neuronpedia

    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. 200862
    Prev
    Next
    INDEX
    Explanations

    serve the transcript and packages

    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
    Phe
    0.43
    rem
    0.43
     bidding
    0.43
     CHAS
    0.40
    呼
    0.39
    hitva
    0.39
     Barriers
    0.39
    openzeppelin
    0.39
    安全
    0.39
    ="|
    0.38
    POSITIVE LOGITS
    ın
    0.51
    شاہ
    0.49
     c
    0.47
     молеку
    0.47
     cust
    0.46
    Пор
    0.46
     versões
    0.45
     versie
    0.44
     تأثير
    0.43
    ولي
    0.43
    Activations Density 0.002%

    No Known Activations