© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6238
    Prev
    Next
    INDEX
    Explanations

    describing adjectives and adverbs

    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
     (__
    0.59
     :\
    0.59
    ifiques
    0.57
     réalisés
    0.57
     "="
    0.55
     Near
    0.54
     $(<
    0.52
    :\
    0.52
    ੱਖ
    0.52
     anc
    0.52
    POSITIVE LOGITS
    sächlich
    0.96
    aneously
    0.83
    istically
    0.81
    heartedly
    0.78
    ingly
    0.77
    的には
    0.76
    imately
    0.75
    යෙන්
    0.73
    ically
    0.72
    antly
    0.72
    Activations Density 0.277%

    No Known Activations