© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5959
    Prev
    Next
    INDEX
    Explanations

    shebang line beginning

    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_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
     cita
    2.01
    epik
    1.88
    Abi
    1.88
     tıkl
    1.87
     uncountable
    1.86
     Acerca
    1.85
    ərbaycan
    1.84
    ṟ
    1.83
     espa
    1.82
    idev
    1.82
    POSITIVE LOGITS
    ør
    1.84
     expect
    1.62
    ance
    1.53
    akia
    1.48
    ORY
    1.48
    wark
    1.45
    antia
    1.43
     Berkshire
    1.42
    нням
    1.42
    ník
    1.42
    Activations Density 0.002%

    No Known Activations