© 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. 6691
    Prev
    Next
    INDEX
    Explanations

    narrow

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

    narrow

    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
    酛
    0.42
    朊
    0.38
     thự
    0.36
    팅
    0.36
    Timestamp
    0.36
    oción
    0.35
    酘
    0.35
    াহি
    0.35
     painless
    0.35
    吘
    0.35
    POSITIVE LOGITS
     narrow
    4.78
     Narrow
    4.56
    narrow
    4.56
    Narrow
    4.56
    狭
    3.92
     narrower
    3.91
     narrowed
    3.89
    窄
    3.80
     narrows
    3.78
     narrowing
    3.77
    Activations Density 0.095%

    No Known Activations