© 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. 684
    Prev
    Next
    INDEX
    Explanations

    while loops

    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
     öt
    1.35
    鞍
    1.33
     sienta
    1.32
     tę
    1.32
     acuerdo
    1.29
     plafond
    1.29
    yfikacja
    1.29
    ंति
    1.26
     hük
    1.26
    śmy
    1.25
    POSITIVE LOGITS
    ⃣
    2.37
    rds
    2.25
    ️⃣
    2.13
    rd
    2.08
    disciplinary
    2.07
    번째
    2.01
    zigen
    1.92
     consecutive
    1.89
    fold
    1.88
    tiered
    1.86
    Activations Density 1.043%

    No Known Activations