© 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. 633
    Prev
    Next
    INDEX
    Explanations

    detailed outline

    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
    aves
    2.59
    upné
    2.56
     useRouter
    2.47
     đảo
    2.32
     heureux
    2.30
    ECs
    2.28
    Shares
    2.27
    룀
    2.26
    जेक्शन
    2.24
    cwnd
    2.23
    POSITIVE LOGITS
    ત્મ
    2.29
     precision
    2.15
     fingert
    2.08
    ოფ
    2.01
     внимания
    2.00
     elaboration
    2.00
    ussion
    1.96
    onaut
    1.95
    DEFG
    1.94
    uating
    1.91
    Activations Density 1.744%

    No Known Activations