© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1928
    Prev
    Next
    INDEX
    Explanations

    in a way

    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_31_width_16k_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
     Excellent
    0.58
    这一点
    0.53
    하나
    0.52
     Perfectly
    0.52
     хуже
    0.52
     மத்தியில்
    0.51
    境
    0.51
    ﺧ
    0.51
     On
    0.50
    处的
    0.50
    POSITIVE LOGITS
     manière
    1.11
     manera
    1.05
     façon
    1.04
     way
    1.02
     manner
    1.00
    的方式
    1.00
     maneira
    1.00
     ways
    0.99
    方式
    0.97
     cách
    0.95
    Activations Density 0.372%

    No Known Activations