© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11411
    Prev
    Next
    INDEX
    Explanations

    included or provided

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

    included or default

    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_40_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
    🕐
    0.44
     ontst
    0.39
     tod
    0.37
    riture
    0.37
    聚合
    0.37
     kater
    0.36
     அற
    0.36
     জ্ঞাত
    0.36
    ̝
    0.35
    ijdens
    0.35
    POSITIVE LOGITS
     included
    2.52
     Included
    2.45
    included
    2.42
    Included
    2.39
     вклю
    1.95
     accompanying
    1.75
     incluido
    1.73
     포함
    1.70
    付属
    1.68
     অন্তর্ভুক্ত
    1.63
    Activations Density 0.509%

    No Known Activations