© 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. 13089
    Prev
    Next
    INDEX
    Explanations

    data conversion or processing

    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
     Đảng
    0.41
    addEnemy
    0.38
    是一种
    0.38
     azért
    0.38
    bė
    0.38
    高达
    0.36
    多种
    0.35
    冈
    0.35
     ▶
    0.35
     ഇത്തരം
    0.35
    POSITIVE LOGITS
     converted
    0.44
     másik
    0.43
     backup
    0.42
    decoded
    0.41
    otro
    0.41
     backups
    0.41
    stro
    0.40
     filtered
    0.38
     adjusted
    0.38
    copy
    0.38
    Activations Density 0.058%

    No Known Activations