© 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. 31-GEMMASCOPE-2-RES-16K
    4. 15326
    Prev
    Next
    INDEX
    Explanations

    funding and awards

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

    grants from NSF

    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
     położ
    0.42
    ί
    0.41
     généralement
    0.40
    分布
    0.40
    ellae
    0.40
     chiesa
    0.39
     urbano
    0.39
    关联
    0.38
     eliminación
    0.38
    ၉
    0.38
    POSITIVE LOGITS
     INSPIRE
    0.46
     salary
    0.46
     sabbatical
    0.46
     HUMAN
    0.44
     वेतन
    0.43
     फीस
    0.43
     ICON
    0.43
     RISE
    0.43
     ICT
    0.43
    つつ
    0.42
    Activations Density 0.070%

    No Known Activations