© 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. 13708
    Prev
    Next
    INDEX
    Explanations

    query parameters

    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
    ෂ්
    1.48
    луйста
    1.45
    aranam
    1.43
     kē
    1.43
    acqua
    1.42
    šení
    1.41
    烨
    1.41
    ্ঞ
    1.41
     शाही
    1.41
    itsi
    1.40
    POSITIVE LOGITS
     intermedi
    1.41
     insurers
    1.32
     Dans
    1.24
     nons
    1.24
     Construct
    1.23
     Ulster
    1.20
     detriment
    1.19
     Vereinigte
    1.18
     Hertfordshire
    1.17
     operatives
    1.17
    Activations Density 0.035%

    No Known Activations