© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12829
    Prev
    Next
    INDEX
    Explanations

    dưới đây là.

    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
    𝘶
    3.10
    WebV
    2.93
    ﺓ
    2.93
     phận
    2.91
    PreferenceKeys
    2.87
    ্তি
    2.87
    𝓇
    2.83
    鸹
    2.82
    ddd
    2.79
    แนน
    2.77
    POSITIVE LOGITS
    ल
    2.96
    ل
    2.86
    y
    2.83
    出典
    2.76
    ی
    2.62
    キュリティ
    2.58
    عرض
    2.58
    িক
    2.57
    ar
    2.53
    পাল
    2.51
    Activations Density 0.001%

    No Known Activations