© 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. 13-GEMMASCOPE-2-RES-16K
    7. 839
    Prev
    Next
    INDEX
    Explanations

    current or future time references

    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_13_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
     later
    0.99
     /-
    0.95
     آج
    0.94
     якого
    0.85
     attualmente
    0.84
     atualmente
    0.84
     প্রতিদিনই
    0.83
     presently
    0.83
    当天
    0.81
     actuellement
    0.81
    POSITIVE LOGITS
    mehr
    1.11
    麗
    1.10
     Königreich
    1.03
    Hab
    1.02
    無論
    1.01
     stär
    1.01
     Gemeins
    1.01
     وفي
    0.99
    看到
    0.99
     republik
    0.98
    Activations Density 0.701%

    No Known Activations