© 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. 240668
    Prev
    Next
    INDEX
    Explanations

    building/construction or political figures

    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
    good
    0.56
    l
    0.51
    banners
    0.47
    CG
    0.46
    mass
    0.45
    datas
    0.45
     wavelengths
    0.45
    more
    0.45
    GOOD
    0.44
     Nicki
    0.44
    POSITIVE LOGITS
     در
    0.49
     في
    0.49
     Break
    0.46
    㠃
    0.46
     リ
    0.45
     Breakthrough
    0.45
    BeforeText
    0.44
     МА
    0.43
     الأوروب
    0.43
     wymag
    0.43
    Activations Density 0.000%

    No Known Activations