© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 37039
    Prev
    Next
    INDEX
    Explanations

    affordable housing, services, healthcare

    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
    ль
    1.99
    ת
    1.78
    什么
    1.77
    на
    1.76
    ுள்ளார்
    1.67
    ன்
    1.59
    什麼
    1.57
     وعلى
    1.53
    ار
    1.47
    </sup>
    1.45
    POSITIVE LOGITS
    m
    1.71
     résulte
    1.62
    ians
    1.60
     Bors
    1.59
     Роз
    1.55
    SECONDS
    1.49
    anos
    1.47
    áno
    1.46
    𝗖
    1.46
     binaries
    1.45
    Activations Density 0.002%

    No Known Activations