© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 224683
    Prev
    Next
    INDEX
    Explanations

    sew, together, uploading

    np_acts-logits-general · gemini-2.5-flash-lite

    Open, meaning, most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1
    0.64
    ↵
    0.55
     highland
    0.53
    to
    0.52
     data
    0.52
     SHF
    0.52
     length
    0.50
     indole
    0.50
    data
    0.49
    ka
    0.49
    POSITIVE LOGITS
    будь
    0.52
    𝕌
    0.52
    সম্পাদকীয়
    0.51
    ологі
    0.50
    ়া
    0.50
    詡
    0.49
     রবিবার
    0.48
    昛
    0.48
    𝘈
    0.48
    竑
    0.48
    Activations Density 0.002%

    No Known Activations