© 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. 751
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

    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
    可能是
    1.11
    otiv
    1.00
    طق
    1.00
     glau
    0.93
    ۆ
    0.92
     INVENTION
    0.92
    ENTION
    0.90
     зару
    0.89
    労
    0.88
    目が
    0.87
    POSITIVE LOGITS
    9
    1.37
    bro
    1.26
     Good
    1.24
    ૯
    1.24
     adjacency
    1.22
    good
    1.21
    
    1.20
     caro
    1.20
    Copies
    1.20
    Returns
    1.18
    Activations Density 0.744%

    No Known Activations