© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1042
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_17_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
     inaugural
    0.98
     rise
    0.96
    的
    0.91
    ulai
    0.84
    ing
    0.84
     የመጀመሪያ
    0.82
     inicia
    0.81
    的双
    0.81
     शुरू
    0.80
    의
    0.80
    POSITIVE LOGITS
     now
    1.33
     الآن
    1.32
     ahora
    1.30
     теперь
    1.23
    Ahora
    1.21
     jetzt
    1.19
    Теперь
    1.18
     тепер
    1.18
     NOW
    1.13
     adesso
    1.13
    Activations Density 0.397%

    No Known Activations