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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 235
    Prev
    Next
    INDEX
    Explanations

    comprehensive language model

    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
     esprim
    1.31
    行う
    1.30
     неуда
    1.29
     afferm
    1.29
     אני
    1.28
    ธุ
    1.28
     classi
    1.27
    ﺣ
    1.27
     ขอ
    1.24
     lắng
    1.24
    POSITIVE LOGITS
    olds
    1.51
    followlike
    1.43
    maked
    1.42
    maan
    1.40
    Objs
    1.37
    ্লিশ
    1.37
    phants
    1.37
    ्यानंतर
    1.36
     Außerdem
    1.35
    tutorials
    1.35
    Activations Density 0.000%

    No Known Activations