© 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. 217259
    Prev
    Next
    INDEX
    Explanations

    corruption in the world

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

    lists such as how many

    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
    呂
    0.49
     ಕ್ಷೇತ್ರದ
    0.48
    丹
    0.48
     głos
    0.47
    ག་
    0.47
    ės
    0.46
    予算
    0.46
    ства
    0.45
    isp
    0.45
    ோ
    0.45
    POSITIVE LOGITS
     I
    0.50
     H
    0.47
     J
    0.46
     Advert
    0.46
     D
    0.46
     W
    0.46
     P
    0.46
     revolutionaries
    0.46
     E
    0.45
     Q
    0.45
    Activations Density 0.000%

    No Known Activations