© 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. 281
    Prev
    Next
    INDEX
    Explanations

    async function

    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
    ла
    2.08
    🏼
    1.89
    ول
    1.87
    🏻
    1.85
    。
    1.80
    <%=
    1.79
    ernetes
    1.77
    ৪
    1.74
    ii
    1.73
    ೭
    1.72
    POSITIVE LOGITS
    न
    2.31
    ف
    2.23
    LE
    2.08
    이랑
    2.00
     solit
    1.88
    rh
    1.79
    س
    1.78
    یر
    1.76
    कमा
    1.76
    م
    1.76
    Activations Density 0.005%

    No Known Activations