© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4121
    Prev
    Next
    INDEX
    Explanations

    named entity recognition and fine-tuning

    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
     recommends
    1.35
    forever
    1.28
    modifier
    1.23
    vary
    1.21
    icosa
    1.19
    꼈
    1.18
    so
    1.18
     initialized
    1.17
    cedure
    1.17
    şı
    1.17
    POSITIVE LOGITS
     ambos
    1.08
    cluso
    1.00
    糺
    0.97
    ‌ی
    0.94
    нный
    0.94
    нном
    0.93
     tê
    0.93
    нного
    0.92
     Heraus
    0.90
    InData
    0.89
    Activations Density 0.082%

    No Known Activations