© 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. 13876
    Prev
    Next
    INDEX
    Explanations

    Masked Language Modeling and Averages

    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
    Archive
    2.07
     Normdatei
    2.07
    ErrorHandler
    2.06
    וה
    2.05
    AFF
    1.95
    rates
    1.89
    ྭ
    1.89
    اداسی
    1.89
    욤
    1.88
    λεύ
    1.88
    POSITIVE LOGITS
     staked
    1.63
    izabeth
    1.62
     diatomic
    1.58
     spectroscopic
    1.55
     pitted
    1.52
    쇠
    1.52
     probability
    1.52
     matched
    1.51
    철
    1.51
     charged
    1.50
    Activations Density 0.019%

    No Known Activations