© 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. 89278
    Prev
    Next
    INDEX
    Explanations

    after certain words

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

    illegal activity

    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
    ,’
    0.43
    u
    0.42
    뎅
    0.42
    elho
    0.41
     uncomment
    0.40
    yt
    0.40
    вости
    0.40
    터
    0.40
    섰
    0.40
    áus
    0.39
    POSITIVE LOGITS
     उत्पन्न
    0.49
     типу
    0.48
     সজ্জিত
    0.48
     באמצעות
    0.47
     ውስጥ
    0.46
     आपूर्ति
    0.46
    ＮＡＮＡ
    0.46
    และการ
    0.45
     கண்டுபிடிக்க
    0.45
    搭載
    0.45
    Activations Density 0.000%

    No Known Activations