© 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. 177590
    Prev
    Next
    INDEX
    Explanations

    phrase followed by to

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

    yes or no answers

    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
     phúc
    0.44
    庆
    0.42
    芑
    0.42
     checkFor
    0.40
    日期
    0.40
    것
    0.40
     cái
    0.39
    EXCEPTION
    0.39
     ngại
    0.39
     kepentingan
    0.39
    POSITIVE LOGITS
    ogh
    0.47
    src
    0.46
    smartphone
    0.45
     ইতিমধ্যেই
    0.43
    ł
    0.43
     взрослых
    0.42
    uing
    0.41
    िशन
    0.41
     swayed
    0.41
     MPEG
    0.41
    Activations Density 0.001%

    No Known Activations