© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14851
    Prev
    Next
    INDEX
    Explanations

    India and ADL

    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
     đỉnh
    1.39
     شد
    1.29
    sels
    1.27
    TacToe
    1.26
    husky
    1.23
    शत
    1.20
    ์
    1.19
    神
    1.18
     وطن
    1.18
    痛苦
    1.17
    POSITIVE LOGITS
    とな
    1.46
     त्यासाठी
    1.40
     oleks
    1.37
     Dafür
    1.34
     obviamente
    1.33
     ESM
    1.30
     précisément
    1.28
     beneficia
    1.27
     certainly
    1.25
     Ando
    1.24
    Activations Density 0.062%

    No Known Activations