© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46672
    Prev
    Next
    INDEX
    Explanations

    cluster shade, cellular composition, collaborative project

    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
    و
    0.51
     biota
    0.51
    t
    0.50
    p
    0.47
     públic
    0.45
     abat
    0.45
     sympathies
    0.44
    úcar
    0.44
     truncate
    0.44
    ⁱ
    0.44
    POSITIVE LOGITS
     повинні
    0.49
     특징
    0.45
     sollten
    0.45
     kerana
    0.45
     наслед
    0.44
     befinden
    0.43
    の違い
    0.43
     ձ
    0.43
     devono
    0.42
     διαφορε
    0.42
    Activations Density 0.002%

    No Known Activations