© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13944
    Prev
    Next
    INDEX
    Explanations

    power supply

    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_7_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
    kosť
    1.79
    elakaan
    1.67
    ∑</
    1.66
     pagare
    1.60
    ristmas
    1.58
     annih
    1.58
     auta
    1.57
     makan
    1.57
     mati
    1.56
     layi
    1.56
    POSITIVE LOGITS
     bulb
    1.54
     bulbs
    1.49
    ш
    1.48
    bulb
    1.43
     notable
    1.38
     expertly
    1.35
     delicate
    1.35
     poignant
    1.34
     chile
    1.33
     signaling
    1.31
    Activations Density 0.185%

    No Known Activations