© 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. 40383
    Prev
    Next
    INDEX
    Explanations

    from running find

    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
    ט
    0.48
    ى
    0.48
    ز
    0.47
    Tema
    0.46
    Problems
    0.45
    Political
    0.44
     computable
    0.44
    Politics
    0.43
    ط
    0.43
    ጀም
    0.43
    POSITIVE LOGITS
     পরিকল্পিত
    0.44
     dinners
    0.43
     périodes
    0.42
    xq
    0.41
    ﺓ
    0.41
     வா
    0.40
    anyl
    0.40
    amental
    0.40
     sinned
    0.40
    apha
    0.40
    Activations Density 0.000%

    No Known Activations