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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5532
    Prev
    Next
    INDEX
    Explanations

    Solar power

    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
    ين
    1.76
    ときは
    1.73
    تان
    1.71
    па
    1.63
    いますが
    1.62
    ě
    1.61
    п
    1.59
    se
    1.56
    یر
    1.51
    تين
    1.50
    POSITIVE LOGITS
     вида
    1.65
     mostr
    1.62
    麼
    1.59
    ১১
    1.56
     financi
    1.55
     allong
    1.54
     inclin
    1.53
     antik
    1.52
    ১৯
    1.50
     vermel
    1.50
    Activations Density 0.004%

    No Known Activations