© 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. 113197
    Prev
    Next
    INDEX
    Explanations

    foreign 'or' constructions

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

    cost function/obedience/boredom

    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
    ет
    0.52
     复
    0.50
    ২০
    0.48
    在此
    0.48
     выхода
    0.46
     пат
    0.45
     десятки
    0.45
    噫
    0.45
    ຕິດຕໍ່
    0.45
    orms
    0.44
    POSITIVE LOGITS
     véh
    0.52
     eller
    0.51
     bzw
    0.49
     senare
    0.47
     veya
    0.46
     stir
    0.46
     yoki
    0.46
     ataupun
    0.45
     ஞ
    0.45
     ök
    0.44
    Activations Density 0.000%

    No Known Activations