© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2236
    Prev
    Next
    INDEX
    Explanations

    modal verbs and negations

    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
     tienden
    1.01
     방정식
    1.00
     نحاول
    0.98
     setia
    0.96
     밀
    0.96
     ricerca
    0.94
     selalu
    0.92
     konsult
    0.92
     SafeArea
    0.92
     beta
    0.89
    POSITIVE LOGITS
     staggering
    1.00
    Какой
    0.95
     shocking
    0.94
    posterous
    0.94
    mere
    0.91
    ֛
    0.90
     Ио
    0.89
     outrageous
    0.89
    Descriptor
    0.89
    ონ
    0.87
    Activations Density 0.781%

    No Known Activations