© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9276
    Prev
    Next
    INDEX
    Explanations

    Bingo Image Creator

    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
    ণ
    1.48
    চর্
    1.42
    জাত
    1.38
     Xcode
    1.30
    ﺤ
    1.30
    ating
    1.28
     circumvent
    1.27
     কই
    1.25
     educa
    1.25
    א
    1.25
    POSITIVE LOGITS
    ្ឋ
    1.46
    ीडी
    1.41
    Bingo
    1.41
    tile
    1.35
    Nag
    1.34
    an
    1.33
    ين
    1.30
    Dun
    1.30
    ים
    1.29
    Baj
    1.29
    Activations Density 0.002%

    No Known Activations