© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8667
    Prev
    Next
    INDEX
    Explanations

    Euler's number e

    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_22_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
     Cleanup
    1.49
    🧼
    1.46
     cleanliness
    1.40
     limpieza
    1.37
    🧹
    1.36
     nettoy
    1.31
     limpeza
    1.29
     Cleaning
    1.28
    🫧
    1.28
     dishwasher
    1.26
    POSITIVE LOGITS
     sympat
    0.81
     informally
    0.80
     sympathetic
    0.79
     modestly
    0.75
     indicated
    0.74
    บุคคล
    0.73
     ascertain
    0.71
    zam
    0.69
    type
    0.69
     formal
    0.69
    Activations Density 0.045%

    No Known Activations