© 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-262K
    7. 10530
    Prev
    Next
    INDEX
    Explanations

    grid pattern

    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_262k_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
    टी
    1.39
    년대
    1.35
    യ
    1.27
    anthropy
    1.25
    я
    1.23
    のア
    1.23
    STRAINT
    1.21
    uya
    1.20
    и
    1.20
     antérieure
    1.20
    POSITIVE LOGITS
     불구하고
    1.92
    Ад
    1.60
    Еще
    1.58
    Бо
    1.55
     controllare
    1.51
     Ansible
    1.48
    
    1.48
    芰
    1.46
    Бі
    1.35
    Бе
    1.34
    Activations Density 0.065%

    No Known Activations