© 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. 14137
    Prev
    Next
    INDEX
    Explanations

    above and beyond

    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
     encountering
    2.14
    boe
    2.12
     앞
    2.05
     prints
    2.05
     volatility
    2.03
    流入
    2.00
     Suff
    2.00
     Qf
    1.99
     evidence
    1.98
     Reign
    1.97
    POSITIVE LOGITS
    ritte
    2.27
    ل
    2.15
    ə
    2.12
    untuk
    2.09
    的な
    2.04
    ियमित
    2.04
    repet
    2.01
     során
    2.00
    method
    2.00
    ंपरा
    1.99
    Activations Density 0.118%

    No Known Activations