© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10191
    Prev
    Next
    INDEX
    Explanations

    asking for clarification or guidance

    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_22_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
     +
    1.01
    न्दा
    0.96
    +
    0.89
    eg
    0.86
     redan
    0.85
    begin
    0.85
    +-
    0.84
     +,
    0.83
    起点
    0.82
    的国家
    0.82
    POSITIVE LOGITS
     last
    4.30
    last
    4.01
     último
    3.95
     terakhir
    3.81
     última
    3.80
     lastly
    3.77
     마지막
    3.72
     LAST
    3.69
     Last
    3.64
     final
    3.63
    Activations Density 0.818%

    No Known Activations