© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 16834
    Prev
    Next
    INDEX
    Explanations

    adjective or adverb followed by completion

    np_acts-logits-general · gemini-2.5-flash-lite

    DPM++ 2M Karras sampler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    
    0.39
     voort
    0.38
     لي
    0.38
    ҳо
    0.38
    实在是
    0.38
    ��
    0.37
    ~(
    0.37
    एफ
    0.36
    бка
    0.36
     الاج
    0.35
    POSITIVE LOGITS
    ，”
    0.53
    কোনও
    0.46
    মত
    0.46
    ,|\
    0.44
    лями
    0.42
    íg
    0.42
     vidé
    0.41
     vá
    0.39
     gleiche
    0.39
     Smartphone
    0.38
    Activations Density 0.024%

    No Known Activations