© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4805
    Prev
    Next
    INDEX
    Explanations

    Finally

    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
    лдуу
    1.24
    oretically
    1.20
    sız
    1.10
    s
    1.10
    e
    1.09
     কিন্ত
    1.06
    𝗮
    1.00
    籙
    1.00
    ্টর
    1.00
     aggregate
    0.99
    POSITIVE LOGITS
    ول
    0.93
    الص
    0.92
    ،
    0.91
    अमेरिका
    0.87
    व
    0.85
    সোমবার
    0.84
    केंद्रीय
    0.83
     BELOW
    0.82
    انہوں
    0.81
    DialogWhenLarge
    0.80
    Activations Density 0.186%

    No Known Activations