© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 876
    Prev
    Next
    INDEX
    Explanations

    GeForce RTX

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    0.87
    ות
    0.87
    দ্ধ
    0.84
     neither
    0.83
    or
    0.80
     तरह
    0.79
     espes
    0.78
    ী
    0.77
     cues
    0.77
     tonne
    0.77
    POSITIVE LOGITS
    ORDER
    0.99
    ONEDB
    0.99
    ر
    0.97
    accro
    0.93
    ระดับ
    0.93
    烙
    0.93
    e
    0.92
    应
    0.91
    اء
    0.89
    绑定
    0.88
    Activations Density 0.001%

    No Known Activations