© 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. 891
    Prev
    Next
    INDEX
    Explanations

    year 2 followed by 0 or 4

    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
    ের
    1.09
    ség
    1.00
    ים
    1.00
    thirds
    0.98
    ات
    0.87
    <0x92>
    0.84
     dígitos
    0.84
    ма
    0.84
    sided
    0.84
    शुदा
    0.81
    POSITIVE LOGITS
    r
    0.92
    l
    0.91
    lly
    0.90
    ri
    0.89
    rifice
    0.89
    ச்சூழ
    0.89
    ro
    0.84
    лни
    0.82
    un
    0.81
    علی
    0.81
    Activations Density 0.075%

    No Known Activations