© 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. 107485
    Prev
    Next
    INDEX
    Explanations

    administration, government, medicine

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

    designed to exploit

    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
     Wale
    0.52
     alkene
    0.48
    н
    0.47
     Shit
    0.46
     ҷ
    0.46
     Nhi
    0.46
     Phang
    0.45
     Kerm
    0.45
    ز
    0.44
     Afd
    0.44
    POSITIVE LOGITS
     fiebre
    0.42
    EI
    0.42
    atributo
    0.42
     আসবে
    0.42
    cuna
    0.42
    এটা
    0.41
     فونبیټ
    0.40
     razones
    0.39
    absorbed
    0.39
    UCH
    0.39
    Activations Density 0.000%

    No Known Activations