© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2505
    Prev
    Next
    INDEX
    Explanations

    percentages, counts, fractions

    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
     hundreds
    0.71
     dozens
    0.63
     projet
    0.59
     +
    0.59
     لمدة
    0.57
     Hundreds
    0.55
    一共
    0.55
     total
    0.54
     सैकड़ों
    0.54
     cientos
    0.54
    POSITIVE LOGITS
     एवरी
    0.56
     সংখ্যাল
    0.54
     всеки
    0.53
    estimator
    0.53
    IENTE
    0.53
     भन्ने
    0.52
    人都
    0.51
     vadanti
    0.51
    苋
    0.51
    likelihood
    0.50
    Activations Density 0.143%

    No Known Activations