© 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. 16-GEMMASCOPE-2-RES-262K
    7. 30316
    Prev
    Next
    INDEX
    Explanations

    thesis structure and formatting

    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_16_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
    ب
    1.14
    ي
    0.95
    د
    0.95
    ج
    0.94
    י
    0.88
    ق
    0.86
    6
    0.85
    ش
    0.85
    स
    0.84
    ד
    0.84
    POSITIVE LOGITS
     be
    0.68
     deviates
    0.64
     standout
    0.59
     sleek
    0.58
     trusty
    0.58
     singly
    0.57
     boast
    0.55
     complied
    0.55
     seashell
    0.55
     quell
    0.54
    Activations Density 0.002%

    No Known Activations