© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1128
    Prev
    Next
    INDEX
    Explanations

    Mid-range, middle class, Middle East, Midjourney

    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_17_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
     prič
    1.01
    үү
    0.90
    ByteBuffer
    0.89
    PPS
    0.88
    각
    0.87
    सबुक
    0.86
    LON
    0.85
     কাট
    0.84
     upp
    0.82
    snap
    0.82
    POSITIVE LOGITS
    fielder
    1.04
     dle
    1.01
    แจ้ง
    1.01
    壢
    0.99
     fielder
    0.95
     sira
    0.92
    дзі
    0.92
    zynarod
    0.90
    vaal
    0.88
    seagreen
    0.88
    Activations Density 0.292%

    No Known Activations