© 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. 5507
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
    ました
    1.05
    ן
    1.00
    cery
    0.96
    ly
    0.93
    cerer
    0.92
    lessly
    0.92
    tronic
    0.89
    inated
    0.89
    nels
    0.87
    sters
    0.86
    POSITIVE LOGITS
     liées
    1.10
     liés
    1.02
    ได้
    1.01
    다음
    1.00
    正
    1.00
    울
    1.00
    우
    0.99
    因此
    0.96
     ہزار
    0.95
    หมาย
    0.95
    Activations Density 0.000%

    No Known Activations