© 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. 138372
    Prev
    Next
    INDEX
    Explanations

    Industrial style or site

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

    foreign languages and context

    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
    ir
    0.49
     প্রাসাদ
    0.47
    산
    0.46
    TING
    0.46
    سي
    0.44
    ตั้งแต่
    0.43
    ess
    0.42
    n
    0.41
    하게
    0.40
     sceptical
    0.39
    POSITIVE LOGITS
     antider
    0.59
    вых
    0.55
     zerstört
    0.52
     ℝ
    0.50
    खास्त
    0.49
     convertir
    0.49
     entornos
    0.48
     franqu
    0.48
     ayudar
    0.47
     entregar
    0.47
    Activations Density 0.001%

    No Known Activations