© 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. 3797
    Prev
    Next
    INDEX
    Explanations

    a series, a sensual, a promising

    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
    s
    2.09
    ों
    1.62
    U
    1.56
    O
    1.54
    מ
    1.52
    га
    1.45
    બ
    1.44
    I
    1.42
    о
    1.42
    EN
    1.41
    POSITIVE LOGITS
    .”[
    1.42
    čni
    1.41
    ه‌ای
    1.34
     veritable
    1.33
    ävät
    1.33
    ğini
    1.32
    enary
    1.31
     ”.
    1.30
    적으로
    1.30
    ilere
    1.28
    Activations Density 0.273%

    No Known Activations