© 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. 1630
    Prev
    Next
    INDEX
    Explanations

    no rights or responsibility

    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
     yatha
    2.30
     slutt
    2.14
     Dadurch
    2.10
    italization
    2.08
    ijt
    2.07
    戙
    2.03
    ງານ
    2.00
    娑
    2.00
    chutz
    1.95
    дить
    1.93
    POSITIVE LOGITS
     clé
    2.34
     неизвест
    1.93
    𝓮
    1.90
     couvert
    1.90
     తెలియ
    1.87
    ારીખ
    1.87
    ProjectType
    1.85
    posing
    1.85
     padx
    1.85
    க்கப்பட்ட
    1.84
    Activations Density 0.239%

    No Known Activations