© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 13744
    Prev
    Next
    INDEX
    Explanations

    stunning scenery and views

    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
    d
    1.59
    ena
    1.37
     custo
    1.34
    ᴅ
    1.27
    iéndose
    1.25
    physiological
    1.23
    ‣
    1.20
    ᴀ
    1.19
    ve
    1.18
    ively
    1.17
    POSITIVE LOGITS
    ки
    1.75
    ция
    1.61
    اً
    1.50
    đer
    1.49
     придется
    1.49
    ции
    1.47
    را
    1.36
     Molding
    1.34
    مة
    1.30
     generalizes
    1.30
    Activations Density 0.058%

    No Known Activations