© 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. 13183
    Prev
    Next
    INDEX
    Explanations

    marketing methods and diagrams

    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
    ⼦
    1.94
    т
    1.81
     ключе
    1.79
    ে
    1.78
    тков
    1.77
     relevante
    1.74
     conteúdo
    1.73
    ﻤ
    1.73
     статті
    1.71
     обзор
    1.70
    POSITIVE LOGITS
    AdapterView
    1.65
    aval
    1.49
    organizations
    1.46
    ilat
    1.40
    embrance
    1.39
    offsetWidth
    1.39
    ark
    1.38
    hrm
    1.36
     Gleich
    1.36
     urbanization
    1.33
    Activations Density 0.099%

    No Known Activations