© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5539
    Prev
    Next
    INDEX
    Explanations

    connection is still

    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_31_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
    oruč
    0.55
     मग
    0.55
    وذ
    0.54
    (|
    0.53
    தோ
    0.52
    துவாக
    0.52
     kolei
    0.52
    ]={
    0.50
    жере
    0.50
    ifdef
    0.50
    POSITIVE LOGITS
     still
    5.13
     Still
    4.47
    still
    4.41
    Still
    4.31
     STILL
    4.19
    仍然
    4.00
     masih
    3.95
     vẫn
    3.89
    仍
    3.75
    依然
    3.66
    Activations Density 0.720%

    No Known Activations