© 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. 92710
    Prev
    Next
    INDEX
    Explanations

    verify, know, and how-to guides

    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
     để
    0.44
     لت
    0.44
     वीं
    0.42
     ము
    0.41
     타
    0.41
     cosplay
    0.40
     protrusion
    0.40
     Speak
    0.40
     อย่า
    0.40
    ারিং
    0.39
    POSITIVE LOGITS
    aughan
    0.42
    sources
    0.42
     superbly
    0.41
    缜
    0.41
    respected
    0.40
    йо
    0.40
     interstices
    0.40
     maestros
    0.39
    ஞ்ஞான
    0.39
    optimized
    0.39
    Activations Density 0.005%

    No Known Activations