© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12037
    Prev
    Next
    INDEX
    Explanations

    very + adverb/adjective

    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
    isOn
    1.22
     aumenta
    1.21
    提高
    1.20
    嶅
    1.20
     bolesti
    1.19
    ධාන
    1.19
     قانون
    1.17
    বছ
    1.17
     เปลี่ยน
    1.16
     ஜனநாயக
    1.16
    POSITIVE LOGITS
     colours
    1.16
     ought
    1.08
     reckon
    1.06
     hearers
    1.02
     honours
    1.00
     names
    0.99
     despatch
    0.98
     paucity
    0.97
     못
    0.97
     thinking
    0.96
    Activations Density 0.039%

    No Known Activations