© 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. 44885
    Prev
    Next
    INDEX
    Explanations

    text before or after

    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
    ות
    1.65
    у
    1.47
    การ
    1.40
    大脑
    1.40
    ма
    1.33
    ים
    1.30
    regation
    1.30
     کریں
    1.27
    Zespół
    1.27
     tačiau
    1.23
    POSITIVE LOGITS
    it
    1.54
    ا
    1.45
    am
    1.43
    很多
    1.29
    ம்பரிய
    1.22
     wardrobes
    1.19
    늉
    1.16
    ae
    1.16
     butchers
    1.14
     কেননা
    1.13
    Activations Density 0.000%

    No Known Activations