© 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. 9371
    Prev
    Next
    INDEX
    Explanations

    explaining how to understand

    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
    бто
    1.23
    คือ
    1.18
     là
    1.17
    )=$
    1.16
     هو
    1.12
     คือ
    1.12
     adalah
    1.11
     syst
    1.04
     Appl
    1.03
    这是
    1.02
    POSITIVE LOGITS
    很好的
    1.35
    很多的
    1.32
    積極的に
    1.31
    꽤
    1.31
     gladly
    1.31
    굉장
    1.30
    非常に
    1.29
     상당히
    1.29
    很多人
    1.29
    不错的
    1.28
    Activations Density 0.125%

    No Known Activations