© 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-262K
    7. 45380
    Prev
    Next
    INDEX
    Explanations

    numbered instructions ending in periods

    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
    ح
    1.20
    나
    1.15
    נו
    1.14
    ول
    1.09
    на
    1.07
    вання
    1.05
    不是
    1.03
    kan
    1.02
    ון
    1.01
    ህል
    1.00
    POSITIVE LOGITS
     felices
    1.12
    n
    1.04
     previo
    1.01
     SupCt
    0.96
     बाकी
    0.96
     Aws
    0.96
    تها
    0.96
    ighted
    0.93
    matically
    0.93
    nX
    0.92
    Activations Density 0.071%

    No Known Activations