© 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. 513
    Prev
    Next
    INDEX
    Explanations

    specific compound words

    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
     ל
    2.22
     ש
    2.10
     Не
    2.06
     בש
    2.04
     לה
    2.03
     如果
    1.90
     ב
    1.89
     За
    1.89
     ز
    1.86
     ل
    1.85
    POSITIVE LOGITS
    Ã
    1.91
    entukan
    1.51
    ick
    1.49
    itos
    1.47
    ¬
    1.43
    Å
    1.40
    ッ
    1.38
    …。
    1.38
    amos
    1.38
     pusat
    1.38
    Activations Density 4.853%

    No Known Activations