© 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. 4733
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and challenges

    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
    ,
    2.73
    ;
    2.47
    ，
    2.41
    ;,
    2.36
    ،
    2.29
    ；
    1.91
     —
    1.90
    ,<
    1.90
     ،
    1.89
    ,​
    1.87
    POSITIVE LOGITS
    ρης
    1.84
    ους
    1.80
    гры
    1.76
     gostaria
    1.69
     пару
    1.67
    фт
    1.66
     vär
    1.64
     Ваш
    1.62
    리카
    1.62
    قع
    1.62
    Activations Density 0.207%

    No Known Activations