© 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. 209155
    Prev
    Next
    INDEX
    Explanations

    researched and, generator, contributor, chip, teach, hammer

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

    ceasefire, agreements, basic states

    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
    creet
    0.47
    겠죠
    0.44
     न्यूयॉर्क
    0.43
     जेव्हा
    0.43
     जिन्हें
    0.43
     imasmim
    0.42
    🕎
    0.42
     النهار
    0.41
    riumph
    0.41
     स्मारक
    0.41
    POSITIVE LOGITS
    جی
    0.55
    を設定
    0.49
    Bol
    0.47
    ವರ
    0.47
     আওতায়
    0.47
    ات
    0.46
    یت
    0.46
    ل
    0.46
    تس
    0.46
     autre
    0.46
    Activations Density 0.000%

    No Known Activations