© 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. 36742
    Prev
    Next
    INDEX
    Explanations

    efficient rechargeable, demographically, prosthetic

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

    prosthetic, Pear, classic

    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
    จ่าย
    0.47
     ဖ
    0.45
     ဝ
    0.44
     ការ
    0.42
    er
    0.41
    awake
    0.41
     日
    0.41
    ņi
    0.40
     lỗi
    0.40
    慢性
    0.40
    POSITIVE LOGITS
     prosthetic
    0.47
     Prost
    0.45
     prost
    0.42
    最高の
    0.42
    cesor
    0.42
    的基础上
    0.42
    基础上
    0.41
    িতেছে
    0.41
     Pear
    0.41
     समस्त
    0.39
    Activations Density 0.000%

    No Known Activations