© 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. 15931
    Prev
    Next
    INDEX
    Explanations

    progression with each instance

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

    progression over steps or iterations

    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
    ртов
    0.43
     konstant
    0.40
    ض
    0.39
    мам
    0.37
     governors
    0.36
     தன்
    0.36
    Formatter
    0.35
    歓
    0.35
    من
    0.35
    د
    0.35
    POSITIVE LOGITS
    當時
    0.46
    ಾಗಿತ್ತು
    0.45
     당시
    0.45
    iculture
    0.43
     erano
    0.43
    ioxid
    0.42
    当时
    0.42
     specifico
    0.41
    ნობ
    0.41
    inois
    0.41
    Activations Density 0.007%

    No Known Activations