© 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. 2556
    Prev
    Next
    INDEX
    Explanations

    product features and durability

    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
    刑
    1.37
     เยอะ
    1.31
    傀
    1.22
    とか
    1.20
     wretched
    1.19
     mấy
    1.18
     ぐらい
    1.17
     iban
    1.17
    多かった
    1.15
     อะไร
    1.15
    POSITIVE LOGITS
     kompakt
    1.59
     adjustable
    1.52
    Compatible
    1.49
    ™
    1.46
     ensures
    1.45
    ™,
    1.44
     elastomer
    1.44
     copolymer
    1.44
     enables
    1.42
     seamlessly
    1.41
    Activations Density 1.602%

    No Known Activations