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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14338
    Prev
    Next
    INDEX
    Explanations

    commercial use

    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
    o
    2.15
    mainloop
    2.14
    oer
    1.98
    uptools
    1.93
    oi
    1.85
    membered
    1.85
     executors
    1.84
    eos
    1.83
    ে
    1.83
    heur
    1.83
    POSITIVE LOGITS
     ">
    1.89
     يكن
    1.86
     podría
    1.85
     Straßen
    1.85
    崆
    1.85
     الكل
    1.84
     Berge
    1.84
     Topical
    1.81
    ﻯ
    1.79
    ITECTURE
    1.79
    Activations Density 0.019%

    No Known Activations