© 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-16K
    7. 14800
    Prev
    Next
    INDEX
    Explanations

    css combinators, variadic, models, left, satisfies, control ID

    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_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
    的重要
    1.01
    빔
    0.92
     adequado
    0.91
    ✧
    0.91
    显著
    0.90
     mágico
    0.89
    mería
    0.89
    的美
    0.87
    ጾ
    0.87
    蒾
    0.86
    POSITIVE LOGITS
    s
    0.99
     boots
    0.84
     capitol
    0.81
     spots
    0.80
     legislatures
    0.80
     complaint
    0.79
     complaints
    0.79
     remarks
    0.77
     displacement
    0.76
     policy
    0.75
    Activations Density 0.000%

    No Known Activations