© 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. 223812
    Prev
    Next
    INDEX
    Explanations

    international labour

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

    Byzantine, vicuña, croissants

    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
     Contempor
    0.42
    Fotos
    0.41
     Sosa
    0.41
    ১৯
    0.40
     Ett
    0.40
    kans
    0.40
     extenso
    0.40
    끊
    0.39
    Tama
    0.39
    ijski
    0.38
    POSITIVE LOGITS
     respecting
    0.58
     allowable
    0.54
     nematode
    0.52
     quaternion
    0.52
     valg
    0.52
     borehole
    0.50
     symplectic
    0.49
     cosine
    0.49
     ciência
    0.49
     distillery
    0.49
    Activations Density 0.000%

    No Known Activations