© 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. 9813
    Prev
    Next
    INDEX
    Explanations

    multiple languages and specific domains

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

    daily updates and reasons

    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
    up
    0.54
    it
    0.51
    indo
    0.51
    je
    0.50
    ian
    0.48
    EM
    0.48
    ul
    0.48
    )
    0.48
    ção
    0.47
    as
    0.47
    POSITIVE LOGITS
    راحی
    0.51
    দন্ত
    0.50
    
    0.50
     insanlar
    0.50
    られない
    0.49
    ৃদ
    0.49
    手的
    0.48
     CLLocation
    0.48
     AGENCY
    0.47
    вик
    0.47
    Activations Density 0.000%

    No Known Activations