© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 197
    Prev
    Next
    INDEX
    Explanations

    prefixes and common endings

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

    labels, font styles

    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_53_width_65k_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
    留在
    0.41
    却没有
    0.39
    สำหรับการ
    0.38
     conceivably
    0.38
    𝘺
    0.38
    郁
    0.38
    可以看到
    0.37
    𝘭
    0.37
    Ꮻ
    0.37
    帕
    0.37
    POSITIVE LOGITS
    odep
    0.61
    ocon
    0.57
    ocont
    0.56
    ocap
    0.54
    epro
    0.54
    ndef
    0.54
    oreg
    0.54
    thand
    0.53
    icom
    0.52
    ocom
    0.52
    Activations Density 0.309%

    No Known Activations