© 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. 83916
    Prev
    Next
    INDEX
    Explanations

    non-English characters

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

    unicode characters

    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
     demonstrate
    0.52
    的核心
    0.51
     cuando
    0.49
     op
    0.48
    ↵
    0.47
     wanneer
    0.46
     quando
    0.46
     bemo
    0.46
     رجل
    0.45
     obe
    0.44
    POSITIVE LOGITS
    <0x80>
    0.59
    tä
    0.58
    ämm
    0.55
    는
    0.52
    ोक
    0.51
    కు
    0.50
    lüğ
    0.50
     divaricatis
    0.49
    t
    0.49
    inata
    0.49
    Activations Density 0.000%

    No Known Activations