Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8405
    Prev
    Next
    INDEX
    Explanations

    stainless steel

    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
    ા
    1.50
     expressões
    1.49
    ा
    1.48
    о
    1.45
    া
    1.41
    忑
    1.36
    を実現
    1.35
    籲
    1.35
     Eles
    1.34
     Forks
    1.30
    POSITIVE LOGITS
    ות
    1.53
    なりません
    1.52
     предме
    1.47
    ׁ
    1.47
    om
    1.45
    songwriter
    1.45
    з
    1.45
    cribed
    1.43
    pecific
    1.42
    ため
    1.41
    Activations Density 0.001%

    No Known Activations