© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77949
    Prev
    Next
    INDEX
    Explanations

    ai impersonation or therapy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     電力
    0.51
    ے
    0.50
    きました
    0.50
    コマンド
    0.48
    ڈنگ
    0.48
     ویت
    0.48
    NASDAQ
    0.47
    サーバー
    0.47
     центре
    0.47
    電力
    0.46
    POSITIVE LOGITS
     //
    0.49
     artik
    0.46
     vetted
    0.46
     outline
    0.45
    进展
    0.45
    es
    0.44
     Hil
    0.44
     Pla
    0.43
     Ra
    0.43
       
    0.43
    Activations Density 0.003%

    No Known Activations