© 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. 14620
    Prev
    Next
    INDEX
    Explanations

    head

    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
    тся
    2.28
    esine
    2.11
    ()=>{
    2.09
     së
    1.91
     Sanit
    1.89
    ти
    1.85
     Seats
    1.77
     Sedangkan
    1.76
     Aladdin
    1.76
    ש
    1.75
    POSITIVE LOGITS
    ين
    2.31
    AZIONE
    2.16
    കര
    2.06
    ك
    1.99
    AV
    1.88
    ाई
    1.88
    มีความ
    1.88
    AKE
    1.87
    ین
    1.84
    ول
    1.81
    Activations Density 0.038%

    No Known Activations