© 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. 68409
    Prev
    Next
    INDEX
    Explanations

    laws and legislation

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

    browser issuesunderstand the codesecurity plans

    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
    are
    0.59
    .
    0.56
    ec
    0.54
    (
    0.53
    ऊ
    0.51
     ferrugine
    0.48
    。
    0.48
    1
    0.48
     是
    0.48
     不需要
    0.48
    POSITIVE LOGITS
     EXE
    0.49
    akath
    0.46
     Dwight
    0.43
    ovjek
    0.43
     جوړونکو
    0.42
    まい
    0.42
    ようになった
    0.42
    ப்பட்டது
    0.41
     FBI
    0.41
     lawmakers
    0.40
    Activations Density 0.001%

    No Known Activations