© 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. 179237
    Prev
    Next
    INDEX
    Explanations

    affecting southern

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

    complex organizations and rejection

    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
    ан
    0.49
     законом
    0.48
    жига
    0.48
     комплекс
    0.46
    чин
    0.45
     lacer
    0.44
    மண
    0.43
    銛
    0.40
    ↵
    0.40
    ुल
    0.40
    POSITIVE LOGITS
     Markt
    0.49
    TERMIN
    0.49
     fief
    0.49
    iranje
    0.48
    np
    0.48
    derabad
    0.47
    sofar
    0.47
     frm
    0.47
    os
    0.47
    ogly
    0.46
    Activations Density 0.000%

    No Known Activations