© 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. 4148
    Prev
    Next
    INDEX
    Explanations

    words starting with re- or weather

    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
    阌
    1.04
    大部分
    0.98
    ари
    0.95
    ok
    0.93
    ा
    0.89
    elasticsearch
    0.87
    ines
    0.87
    monospace
    0.86
    𝚑
    0.84
    ience
    0.83
    POSITIVE LOGITS
    ণ
    1.46
    ów
    1.38
    ת
    1.35
    ্স
    1.32
    门口
    1.30
     Estoy
    1.30
    ación
    1.28
    larımız
    1.27
    ную
    1.26
    นี้
    1.26
    Activations Density 0.025%

    No Known Activations