© 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. 15142
    Prev
    Next
    INDEX
    Explanations

    quote

    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
     সংক্রমণের
    0.52
    fo
    0.50
    //}
    0.47
    {{{
    0.47
     πά
    0.46
    //@
    0.45
     perfor
    0.45
    Rex
    0.45
    ($"{
    0.45
    //
    0.45
    POSITIVE LOGITS
    大多數
    0.64
     ఆర్థిక
    0.59
    orsanız
    0.58
    大多数
    0.57
     большинство
    0.57
     ಆದ್ದರಿಂದ
    0.55
    લાઇ
    0.55
     большин
    0.54
     maioria
    0.54
     Alemanha
    0.54
    Activations Density 0.008%

    No Known Activations