© 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. 242492
    Prev
    Next
    INDEX
    Explanations

    religious texts or law

    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
     "****
    0.43
     범
    0.42
     วิ
    0.42
     wnętr
    0.42
     positiv
    0.42
    โย
    0.41
    เขต
    0.40
     fach
    0.40
     使っ
    0.40
     는
    0.39
    POSITIVE LOGITS
     Productos
    0.50
     अध्याय
    0.49
     diseñado
    0.48
     ensayos
    0.47
    acijama
    0.46
     dạng
    0.46
     doulou
    0.44
     заявления
    0.44
    том
    0.44
     Mỹ
    0.44
    Activations Density 0.000%

    No Known Activations