© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8292
    Prev
    Next
    INDEX
    Explanations

    obviously

    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
     ఎక్కువగా
    0.65
    𝐛
    0.59
    യാണ്
    0.54
     pourrait
    0.54
    下列
    0.54
    𝐰
    0.54
     unusually
    0.52
     ressembl
    0.51
    𝐚
    0.50
    尔多
    0.49
    POSITIVE LOGITS
     obviously
    4.22
     Obviously
    3.78
    Obviously
    3.77
    obviously
    3.75
     ovviamente
    3.72
     oczywiście
    3.69
    当然
    3.56
    當然
    3.47
     évidemment
    3.45
     obviamente
    3.36
    Activations Density 0.687%

    No Known Activations