© 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. 45533
    Prev
    Next
    INDEX
    Explanations

    mTOR, onda, CFT, mice, City

    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
    d
    1.90
    فة
    1.74
     Старки
    1.59
    ING
    1.57
     Министерство
    1.54
    asarray
    1.53
    𝘋
    1.52
     cuales
    1.52
    Setelah
    1.48
    corr
    1.45
    POSITIVE LOGITS
    であり
    1.69
    ians
    1.68
    ра
    1.59
     chlorides
    1.59
    要想
    1.59
    ح
    1.59
     goddesses
    1.57
     অনেকেই
    1.56
    ان
    1.55
    น
    1.55
    Activations Density 0.001%

    No Known Activations