© 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. 16537
    Prev
    Next
    INDEX
    Explanations

    Names followed by continuation

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

    however, but, furthermore

    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
     pierwsze
    0.45
     firstly
    0.45
     playoff
    0.41
     اول
    0.40
     első
    0.40
     عدد
    0.39
     første
    0.39
    톱
    0.39
     levers
    0.39
     first
    0.38
    POSITIVE LOGITS
     weiterer
    0.48
     dalej
    0.46
     தொடர்ந்து
    0.43
    さらに
    0.43
     selanjutnya
    0.42
     Weitere
    0.41
     Aplikasi
    0.41
    ếu
    0.41
     Increased
    0.40
    anjutnya
    0.40
    Activations Density 0.036%

    No Known Activations