© 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. 101940
    Prev
    Next
    INDEX
    Explanations

    foreign words and characters

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

    website creation data

    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
    u
    0.49
     Salary
    0.48
     Archives
    0.45
     Plates
    0.45
     Traders
    0.45
    htp
    0.44
     Nerve
    0.44
     तोह
    0.44
     Equipment
    0.43
     Squadron
    0.43
    POSITIVE LOGITS
    юнча
    0.51
     handelt
    0.49
    仔
    0.49
    噪声
    0.47
    сто
    0.47
     deutlich
    0.46
    㕫
    0.46
     heeft
    0.46
    öll
    0.44
    ‌اند
    0.44
    Activations Density 0.001%

    No Known Activations