© 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-16K
    7. 830
    Prev
    Next
    INDEX
    Explanations

    connect or consult with

    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_16k_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
    ú
    0.48
    注释
    0.48
    áról
    0.46
     זה
    0.45
     коммента
    0.44
     グ
    0.44
     વખ
    0.44
     ил
    0.43
     言っ
    0.43
    这一切
    0.43
    POSITIVE LOGITS
     with
    0.84
     avec
    0.75
     dengan
    0.70
     với
    0.68
    กับ
    0.65
    dengan
    0.65
     interact
    0.62
     interacts
    0.61
     someone
    0.59
     Interaction
    0.59
    Activations Density 0.119%

    No Known Activations