© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9484
    Prev
    Next
    INDEX
    Explanations

    focus on what matters

    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_40_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
     in
    0.53
    着
    0.47
     ervoor
    0.44
    韆
    0.43
     적극
    0.42
    仅
    0.42
    excel
    0.42
    lang
    0.41
     sobretudo
    0.41
    avras
    0.41
    POSITIVE LOGITS
     miraculously
    0.49
    וח
    0.48
    🔥🔥
    0.48
     внимания
    0.47
    स
    0.46
     sharpen
    0.45
     вигляді
    0.45
    ilta
    0.45
     върху
    0.44
    é
    0.44
    Activations Density 0.124%

    No Known Activations