© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2514
    Prev
    Next
    INDEX
    Explanations

    sql commands

    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
     brandy
    2.15
     nguồn
    2.13
    ⁺
    2.06
    余额
    1.96
     contato
    1.93
     Boise
    1.93
    wallet
    1.89
     Orion
    1.89
    縁
    1.88
     lensa
    1.88
    POSITIVE LOGITS
     convuls
    0.88
     witnessing
    0.87
    俑
    0.86
     tribunals
    0.83
     حاضر
    0.81
    exempl
    0.79
    प्रदर्शन
    0.79
     witnessed
    0.74
     describ
    0.72
    缉
    0.71
    Activations Density 0.082%

    No Known Activations