© 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. 13734
    Prev
    Next
    INDEX
    Explanations

    LC, ECC, factor, holding, cost

    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
    जीशन
    2.46
    ipennis
    2.43
    ра
    2.39
     приблизи
    2.37
    seconds
    2.32
     permitido
    2.31
    й
    2.29
    atorios
    2.28
    нное
    2.26
    milliseconds
    2.22
    POSITIVE LOGITS
     duk
    2.07
    ajj
    2.00
    uş
    1.97
    ′
    1.96
     δ
    1.88
    yeong
    1.79
     مطرح
    1.78
     kan
    1.78
     لام
    1.78
    ++',
    1.77
    Activations Density 0.000%

    No Known Activations