© 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. 4391
    Prev
    Next
    INDEX
    Explanations

    underground tunnels and related concepts

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

    underground tunnels and subterranean places

    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
     പിടി
    0.44
    parvec
    0.40
    amanam
    0.39
    嫋
    0.39
     آموز
    0.39
    ائض
    0.39
     پیس
    0.38
     বাদী
    0.38
    袅
    0.38
    ကလေး
    0.38
    POSITIVE LOGITS
     underground
    3.55
     подзем
    3.34
     subterranean
    3.16
    地下
    3.14
     Underground
    3.06
     지하
    2.98
     tunnels
    2.94
     subterr
    2.83
     tunnel
    2.78
     Tunnel
    2.52
    Activations Density 0.130%

    No Known Activations