© 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. 5216
    Prev
    Next
    INDEX
    Explanations

    names and dialogue markers

    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
     diad
    0.97
    đer
    0.93
    зирован
    0.89
     Scattered
    0.88
    殻
    0.88
     condimentum
    0.88
    낱
    0.86
    Variants
    0.85
    opolitan
    0.85
     według
    0.85
    POSITIVE LOGITS
    sons
    2.10
    ocking
    2.06
     robbing
    2.04
    啱
    2.00
    ходите
    1.98
     (#{
    1.94
     التى
    1.94
     minimising
    1.93
     analysing
    1.93
     solicitors
    1.92
    Activations Density 0.190%

    No Known Activations