© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4509
    Prev
    Next
    INDEX
    Explanations

    owner / ownership

    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
    寒
    1.63
    加拿大
    1.50
     Шве
    1.49
    CPP
    1.42
    加拿
    1.41
    比利
    1.37
    🇨
    1.36
     Scandinavia
    1.35
     cush
    1.33
    🥶
    1.33
    POSITIVE LOGITS
     owners
    2.37
    owners
    2.36
     Owners
    2.35
     owner
    2.35
     propietario
    2.27
     propietarios
    2.27
     Owner
    2.24
     ownership
    2.24
     OWNER
    2.16
     propriétaires
    2.16
    Activations Density 0.049%

    No Known Activations