© 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-65K
    7. 2361
    Prev
    Next
    INDEX
    Explanations

    long-term

    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_65k_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
    اء
    3.36
    𝐞
    2.90
    ยนต์
    2.89
    𝐚
    2.62
    다고
    2.60
    st
    2.60
    𝐮
    2.52
    ık
    2.45
    요
    2.37
    𝐬
    2.34
    POSITIVE LOGITS
    pportun
    2.50
    𝓁
    2.24
    ристи
    2.21
    া
    2.15
    𝒹
    2.09
     flog
    2.09
    ҝ
    2.08
     brach
    2.08
     Kudos
    2.06
    ing
    2.03
    Activations Density 0.240%

    No Known Activations