© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7527
    Prev
    Next
    INDEX
    Explanations

    money loss and returns

    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
    孳
    1.03
     köz
    0.96
     dign
    0.96
    wohner
    0.96
    dependencies
    0.95
     publica
    0.95
    Dependency
    0.95
    賑
    0.95
    退休
    0.95
     linkages
    0.94
    POSITIVE LOGITS
     doubting
    1.14
     convinced
    1.07
     Mistakes
    1.06
     vestibular
    1.04
     Configur
    1.03
     Dino
    1.01
    عار
    1.01
     Dinosaur
    0.98
     Classic
    0.98
     mistakes
    0.97
    Activations Density 0.262%

    No Known Activations