© 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. 241826
    Prev
    Next
    INDEX
    Explanations

    Centre, game, mortgage, rock, Turkish

    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
    지와
    0.58
     legy
    0.49
     geslacht
    0.48
    膨
    0.47
    친
    0.47
    繋がり
    0.47
    案
    0.47
    tochy
    0.46
     Aprili
    0.46
    薨
    0.46
    POSITIVE LOGITS
    Embed
    0.51
    ↵↵
    0.49
    ↵
    0.49
    visions
    0.48
    UnderTest
    0.47
     ROI
    0.47
    ern
    0.47
     Clive
    0.47
    era
    0.47
     Richard
    0.46
    Activations Density 0.000%

    No Known Activations