© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 569
    Prev
    Next
    INDEX
    Explanations

    Hungarian and Turkish phrases

    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
     coupled
    1.23
     achieving
    1.06
     seemingly
    1.05
     tailored
    1.04
     這
    1.03
     decidedly
    1.00
    AssetsResponse
    1.00
    PerTrial
    1.00
    MessageNow
    0.99
    <unused852>
    0.99
    POSITIVE LOGITS
     k
    0.98
     kont
    0.94
     akt
    0.90
     kal
    0.90
     kom
    0.90
     kol
    0.90
     ka
    0.88
     kon
    0.87
     kir
    0.86
     kas
    0.85
    Activations Density 0.052%

    No Known Activations