© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14559
    Prev
    Next
    INDEX
    Explanations

    conditions of anonymity

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

    technical phrases and keywords

    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_31_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
     antik
    0.50
     restorative
    0.47
    ৰ
    0.44
     balk
    0.43
    Metro
    0.43
     metro
    0.42
     Restoration
    0.42
    お
    0.41
    おそらく
    0.41
     preko
    0.40
    POSITIVE LOGITS
    мом
    0.52
    会导致
    0.50
     কালিক
    0.46
    ivar
    0.46
     xương
    0.46
     جدول
    0.44
     следующие
    0.44
    britann
    0.44
     структуру
    0.44
     لکھنے
    0.44
    Activations Density 0.000%

    No Known Activations