© 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. 14681
    Prev
    Next
    INDEX
    Explanations

    Finnish, ell, arr, Dess

    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
    ch
    2.50
    ้
    2.20
    ం
    2.11
    ı
    1.95
    부터
    1.91
    quí
    1.86
    chus
    1.86
    ija
    1.85
    <0x80>
    1.84
    WEL
    1.84
    POSITIVE LOGITS
    ק
    2.47
     laborer
    2.44
    راً
    2.41
     ค่ะ
    2.28
     fervor
    2.20
     internalized
    2.19
     أيضاً
    2.17
     stabilizes
    2.06
     Maß
    2.05
     fertilizer
    2.03
    Activations Density 0.425%

    No Known Activations