© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13678
    Prev
    Next
    INDEX
    Explanations

    Saturday: schedule items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ereich
    1.61
    ej
    1.61
    j
    1.59
     Einstellung
    1.57
    zeit
    1.56
    ലു
    1.50
    illä
    1.46
     Zeitpunkt
    1.44
    əsi
    1.44
    ib
    1.44
    POSITIVE LOGITS
     gleaming
    2.13
     masterpiece
    2.04
     solemn
    2.03
     feast
    2.00
     devoured
    1.99
     peering
    1.90
     vaulted
    1.88
    ｿ
    1.87
     xī
    1.83
     qīng
    1.83
    Activations Density 0.004%

    No Known Activations