© 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. 43416
    Prev
    Next
    INDEX
    Explanations

    either positive or negative

    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
     ϒ
    1.02
     Errors
    0.99
     GIR
    0.98
     Características
    0.97
     HOR
    0.95
     Química
    0.95
     Vivid
    0.95
     Mé
    0.95
     Cite
    0.95
     Câu
    0.95
    POSITIVE LOGITS
    。
    1.18
    ।
    1.13
    ，
    1.02
    上
    1.00
    f
    0.98
    られる
    0.93
    会
    0.92
    할
    0.92
     aide
    0.91
    え
    0.90
    Activations Density 0.000%

    No Known Activations