Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 12-GEMMASCOPE-2-RES-16K
    4. 43
    Prev
    Next
    INDEX
    Explanations

    lists starting with "This"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AND
    0.40
     you
    0.38
     IANS
    0.38
     данной
    0.38
     riferimento
    0.38
    ஐ
    0.38
    और
    0.37
     and
    0.37
    {~
    0.37
     eventuali
    0.37
    POSITIVE LOGITS
     জানিয়েছিলেন
    0.45
    н
    0.42
     realizaron
    0.42
     miraculously
    0.41
    iyordu
    0.41
     renforcer
    0.41
    ν
    0.40
     reimag
    0.40
    وكان
    0.40
    apons
    0.39
    Activations Density 2.319%

    No Known Activations