© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7868
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, or multilingual elements

    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
    ال
    2.83
    ين
    2.78
    ب
    2.48
    ς
    2.47
    s
    2.45
    ع
    2.30
    THING
    2.23
    ့
    1.95
    oretically
    1.93
    ਰ
    1.91
    POSITIVE LOGITS
    zelfde
    2.27
    1.98
    на
    1.93
    )$,
    1.91
    ore
    1.80
    ют
    1.80
    iled
    1.80
    ication
    1.73
    ти
    1.71
    icient
    1.70
    Activations Density 0.101%

    No Known Activations