© 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. 1508
    Prev
    Next
    INDEX
    Explanations

    non-latin scripts

    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
     bienvenidos
    1.27
     serta
    1.24
     hermana
    1.24
    などの
    1.21
     calme
    1.16
    玑
    1.13
     Grèce
    1.12
     seluruh
    1.11
     cantidad
    1.11
     naturale
    1.11
    POSITIVE LOGITS
    LEXPORT
    1.13
    ிரி
    1.10
     }*/
    1.10
     esters
    1.05
     strokes
    1.04
     ইলেক্ট্রোলাই
    1.03
    WAL
    1.00
     pointers
    0.99
    _="
    0.97
    rune
    0.96
    Activations Density 0.145%

    No Known Activations