© 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. 44456
    Prev
    Next
    INDEX
    Explanations

    CA service

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

    JavaScript Function, Logic

    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
     Алексе
    0.53
     أَ
    0.52
     acúst
    0.50
     ações
    0.50
     núcleo
    0.49
     愛
    0.49
    șa
    0.48
     Até
    0.48
    Yep
    0.48
     любят
    0.48
    POSITIVE LOGITS
    ุ
    0.47
     تبدیل
    0.47
    ᵢ
    0.46
     کو
    0.46
    をや
    0.45
    transfer
    0.44
     یا
    0.43
    وڑا
    0.43
    üre
    0.43
    ڑے
    0.42
    Activations Density 0.000%

    No Known Activations