© 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. 69000
    Prev
    Next
    INDEX
    Explanations

    published if, hearing or, selections are

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

    offensive generalizations

    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
     Integrative
    0.43
    एस
    0.42
    怡
    0.41
     integrator
    0.41
    Rebecca
    0.40
    इजेशन
    0.40
    resistance
    0.39
    AuthController
    0.38
    epsilon
    0.38
     Rebecca
    0.38
    POSITIVE LOGITS
     យើង
    0.44
     существует
    0.44
    我們可以
    0.43
     &
    0.42
     effett
    0.41
     amenaza
    0.41
     Hence
    0.41
     витра
    0.41
    nable
    0.41
     элементы
    0.40
    Activations Density 0.003%

    No Known Activations