© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104687
    Prev
    Next
    INDEX
    Explanations

    rules, compliance, and violations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Зачем
    -1.41
    Только
    -1.15
    静岡
    -1.09
    Якщо
    -1.08
    東北
    -1.08
    🎍
    -1.03
    After
    -1.02
    Интере
    -1.00
    There
    -0.99
    Где
    -0.99
    POSITIVE LOGITS
     comply
    1.24
    符合
    1.22
     according
    1.20
     zgodnie
    1.10
     compliant
    1.04
     aplicar
    1.02
     complies
    1.01
     ตาม
    1.00
     volgens
    1.00
     complying
    0.98
    Activations Density 0.231%

    No Known Activations