© 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. 13135
    Prev
    Next
    INDEX
    Explanations

    oak trees

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

    currencies issued by governments

    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
    エ
    0.52
    ING
    0.51
     Guo
    0.51
    ฟ
    0.51
    Ф
    0.50
    フェ
    0.50
    菽
    0.49
    ुल
    0.48
     ByteBuffer
    0.46
    g
    0.46
    POSITIVE LOGITS
     entschied
    0.47
     اجمع
    0.45
    ð
    0.45
     oak
    0.43
    គឺ
    0.43
    breed
    0.42
    oak
    0.41
     তাদেরকে
    0.41
     thi
    0.41
     oaks
    0.41
    Activations Density 0.000%

    No Known Activations