© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9548
    Prev
    Next
    INDEX
    Explanations

    if you don't have

    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
    <start_of_image>
    0.88
     says
    0.75
     intelligible
    0.73
     des
    0.73
     smiles
    0.71
     lap
    0.71
     is
    0.70
    สวย
    0.70
     not
    0.70
     pink
    0.70
    POSITIVE LOGITS
    Diethyl
    1.29
    楖
    1.28
     প্যাকে
    1.24
    তর
    1.23
    <unused1544>
    1.22
    山本
    1.21
     জাহাজ
    1.21
    ഭ്യാസ
    1.20
    ्योपै
    1.20
    diethyl
    1.19
    Activations Density 0.013%

    No Known Activations