© 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. 14277
    Prev
    Next
    INDEX
    Explanations

    data integrity

    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
    𝚍
    3.39
    𝚢
    2.94
    𝚒
    2.84
    𝚜
    2.76
    𝚔
    2.70
    𝓀
    2.64
    𝚎
    2.62
    basicConfig
    2.56
    𝚂
    2.50
    ঃখ
    2.50
    POSITIVE LOGITS
    t
    5.15
    т
    3.83
    ের
    3.70
    s
    3.64
    u
    3.53
    ség
    3.50
    ي
    3.42
    tog
    3.37
    ි
    3.30
    dır
    3.21
    Activations Density 0.005%

    No Known Activations