© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10732
    Prev
    Next
    INDEX
    Explanations

    sense of

    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
     poison
    1.04
     poisons
    1.04
     brewer
    1.02
     jeweler
    1.01
     magist
    1.00
     carcinogenic
    0.98
     Poison
    0.98
    毒
    0.98
     potion
    0.96
     alkaloids
    0.96
    POSITIVE LOGITS
     witnesses
    1.21
     testimony
    1.20
     témoins
    1.17
     sighting
    1.17
     testimonies
    1.15
    witness
    1.14
     witness
    1.14
     testigos
    1.13
     testim
    1.12
     testimon
    1.12
    Activations Density 0.178%

    No Known Activations