© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40996
    Prev
    Next
    INDEX
    Explanations

    who something

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

    making use of examples

    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
     ね
    0.53
    圖片
    0.52
    ੁ
    0.51
    об
    0.49
    та
    0.49
    ਾਰ
    0.48
    ӳ
    0.47
    리의
    0.47
    ः
    0.47
    ress
    0.47
    POSITIVE LOGITS
     fyra
    0.48
     xyl
    0.47
    Luong
    0.46
     fo
    0.45
     vont
    0.44
     tuv
    0.43
     توجہ
    0.43
     kated
    0.43
     paraffin
    0.42
     Stuttgart
    0.42
    Activations Density 0.000%

    No Known Activations