© 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. 219632
    Prev
    Next
    INDEX
    Explanations

    designing spaces

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

    operator, team configurations

    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
     recitation
    0.45
     ď
    0.43
    共
    0.42
    ్య
    0.42
     टू
    0.41
     pell
    0.39
     coch
    0.38
    共有
    0.38
    誇
    0.38
     hygien
    0.38
    POSITIVE LOGITS
    তামূলক
    0.48
    の商品は
    0.46
    wolves
    0.46
    上帝
    0.46
     Configurations
    0.44
    perd
    0.44
     வடிவமை
    0.44
     espèce
    0.43
     ανθρώ
    0.43
     installé
    0.43
    Activations Density 0.001%

    No Known Activations