© 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. 17847
    Prev
    Next
    INDEX
    Explanations

    collecting taxes

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

    tangent line, understanding, seeing, measuring

    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
    ・
    0.54
    Kom
    0.51
    Disha
    0.50
    的山
    0.49
    ベリー
    0.49
    ーカー
    0.48
    发生的
    0.48
    铛
    0.48
    avas
    0.47
    Date
    0.47
    POSITIVE LOGITS
     vetro
    0.49
     indexes
    0.49
     indices
    0.46
     marinas
    0.45
     topology
    0.45
     longitudinal
    0.44
     top
    0.44
     oasis
    0.44
     Tony
    0.44
     aviation
    0.44
    Activations Density 0.000%

    No Known Activations