© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1895
    Prev
    Next
    INDEX
    Explanations

    multilingual texts, code, emails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     Taehyung
    1.21
     확보
    1.17
     생각
    1.16
     basaltes
    1.16
    맇
    1.15
     mischiev
    1.14
     Sasuke
    1.12
     Mbps
    1.11
     sebagaimana
    1.11
     Fläche
    1.11
    POSITIVE LOGITS
    斯
    0.85
    阿
    0.84
    弗
    0.80
    ฮ
    0.80
    约翰
    0.78
    エ
    0.77
    卡
    0.76
    א
    0.75
    帕
    0.73
    雷
    0.73
    Activations Density 0.043%

    No Known Activations