© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4373
    Prev
    Next
    INDEX
    Explanations

    thought-provoking content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     visitas
    1.50
     метою
    1.45
    ignores
    1.44
    ուս
    1.43
    再加上
    1.42
    ὸ
    1.41
    োদিত
    1.40
     četiri
    1.39
     اکت
    1.39
    承受
    1.39
    POSITIVE LOGITS
    いただ
    0.95
    ën
    0.92
    riebe
    0.90
    yb
    0.88
    heets
    0.88
    }`,
    0.88
     consol
    0.88
    hé
    0.86
     kol
    0.86
     triplets
    0.86
    Activations Density 0.048%

    No Known Activations