© 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. 15311
    Prev
    Next
    INDEX
    Explanations

    but also

    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
    ного
    1.30
    u
    1.07
    cell
    1.05
    uern
    1.05
    <0xA7>
    1.04
    न्या
    0.99
    angled
    0.98
    櫳
    0.98
    ড়াল
    0.96
    a
    0.95
    POSITIVE LOGITS
     což
    1.13
     naïve
    1.09
    스와
    1.08
     که
    1.06
     that
    0.98
     такие
    0.96
    вый
    0.94
     давление
    0.93
     worse
    0.91
     dó
    0.91
    Activations Density 0.019%

    No Known Activations