© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 30682
    Prev
    Next
    INDEX
    Explanations

    pronounce or pronunciation

    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
    aa
    1.97
    िया
    1.87
    ية
    1.85
    t
    1.73
     TRANSPORTURI
    1.66
    ानुसार
    1.65
     upay
    1.63
    ларга
    1.62
     ennek
    1.60
    க்கிழ
    1.57
    POSITIVE LOGITS
    ש
    1.83
    G
    1.58
    s
    1.55
     Landmarks
    1.54
    ко
    1.51
     
    1.51
     Guilty
    1.49
    х
    1.48
     Pelicans
    1.47
    に従
    1.43
    Activations Density 0.006%

    No Known Activations