© 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. 117222
    Prev
    Next
    INDEX
    Explanations

    if / used / first / to

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

    asking questions or discussing topics

    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
     politik
    0.48
     brands
    0.47
    民众
    0.46
    াকুর
    0.46
    នោះ
    0.45
    রাষ্ট্রে
    0.45
    鹖
    0.45
     statistik
    0.44
     hozzá
    0.44
     কূটনীতিক
    0.44
    POSITIVE LOGITS
    ೕ
    0.55
    abin
    0.52
     elated
    0.51
    0
    0.50
    ̄
    0.48
    and
    0.47
    喪
    0.46
    ｰ
    0.45
     للإ
    0.45
     erine
    0.45
    Activations Density 0.001%

    No Known Activations