© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8501
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    郓
    0.96
    rocessing
    0.93
    thren
    0.90
     Excellency
    0.89
    gleichen
    0.85
     Etiquetas
    0.84
    ুইস
    0.84
     Suu
    0.84
     plazo
    0.83
     उपराष्ट्रपति
    0.83
    POSITIVE LOGITS
    ش
    1.02
    ز
    0.92
    ف
    0.88
    تش
    0.86
    т
    0.85
    াজ
    0.84
    ব
    0.82
    り
    0.81
    여
    0.80
    تان
    0.79
    Activations Density 0.000%

    No Known Activations