© 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. 3759
    Prev
    Next
    INDEX
    Explanations

    images and streaming video

    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
    setHeader
    0.38
    Header
    0.38
    During
    0.38
    firefox
    0.38
     개인
    0.37
    beatCounter
    0.37
     번
    0.37
    াইজ
    0.37
    ierz
    0.37
     떠
    0.37
    POSITIVE LOGITS
    PHAM
    0.50
    ammlung
    0.42
    ksh
    0.41
     licensure
    0.41
     supplemented
    0.41
    陏
    0.41
     deliverables
    0.41
    formes
    0.39
     Images
    0.39
     undisputed
    0.39
    Activations Density 0.008%

    No Known Activations