© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5519
    Prev
    Next
    INDEX
    Explanations

    narrative transition introducing events

    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_13_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
    ジオ
    0.88
    铅
    0.84
    اديم
    0.78
    럇
    0.76
    inium
    0.74
    ство
    0.73
    вис
    0.73
    อกจาก
    0.72
    نيا
    0.72
    뺏
    0.71
    POSITIVE LOGITS
     Jacques
    1.36
     Arnaud
    1.36
     Alain
    1.30
     CL
    1.29
     TR
    1.28
     Francois
    1.27
    Jacques
    1.25
     Rehman
    1.24
     Alexandre
    1.23
    Commenting
    1.22
    Activations Density 0.100%

    No Known Activations