© 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. 15649
    Prev
    Next
    INDEX
    Explanations

    unique or specific concepts

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

    unique, novel, or specific descriptions

    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
    <unused13>
    0.44
    <unused67>
    0.42
     zina
    0.38
    ợp
    0.38
    <unused18>
    0.38
     веществ
    0.38
     ज्यात
    0.37
    डेंट
    0.37
    <unused56>
    0.37
    ">'
    0.36
    POSITIVE LOGITS
     уника
    0.54
     अनो
    0.54
     quirky
    0.50
     অদ্ভুত
    0.50
     eponymous
    0.48
    จทย์
    0.46
     idiosyncratic
    0.46
     необы
    0.46
     uniqueness
    0.46
     বাংলাদেশি
    0.45
    Activations Density 0.288%

    No Known Activations