© 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. 5083
    Prev
    Next
    INDEX
    Explanations

    enumerate options or reasons

    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
     дальше
    2.55
    SwingConstants
    2.51
     другие
    2.51
    󠁮
    2.46
     ähn
    2.45
     weitere
    2.44
     других
    2.43
     även
    2.42
    也可以
    2.42
    なども
    2.41
    POSITIVE LOGITS
    •
    1.90
     •
    1.88
    first
    1.86
     first
    1.86
     firstly
    1.82
    ·
    1.77
     *
    1.74
     Firstly
    1.73
    *
    1.69
     
    1.65
    Activations Density 0.207%

    No Known Activations