© 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. 43072
    Prev
    Next
    INDEX
    Explanations

    qualified words and phrases

    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
    <0x0D>
    0.44
     ammonium
    0.44
     Aviation
    0.43
    fileID
    0.40
     V
    0.40
     Andorra
    0.38
     Madrid
    0.38
    iov
    0.37
    msbuild
    0.37
    step
    0.37
    POSITIVE LOGITS
     hoş
    0.53
    哫
    0.52
     მ
    0.51
    💐
    0.50
    larınız
    0.50
    ları
    0.49
     ใคร
    0.49
     갔
    0.48
    参赛
    0.48
     byproduct
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.