© 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. 4081
    Prev
    Next
    INDEX
    Explanations

    hobbits home

    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
    al
    1.26
    l
    1.09
    ма
    1.07
    ה
    1.06
    ל
    1.05
     ی
    1.03
    ک
    1.02
    מ
    1.02
    ed
    1.02
    ’
    0.97
    POSITIVE LOGITS
    يران
    1.00
    يرين
    0.94
    тник
    0.93
    ঙ্কার
    0.89
    त्रियों
    0.87
    \
    0.86
     partito
    0.84
    روف
    0.82
     fielder
    0.82
    矯
    0.82
    Activations Density 0.233%

    No Known Activations