© 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. 15256
    Prev
    Next
    INDEX
    Explanations

    Elasticsearch

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

    text after asterisks

    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
     আহমে
    0.44
    焼
    0.43
    定理
    0.42
    優
    0.42
     calves
    0.42
     रच
    0.42
    範
    0.42
     যানবাহন
    0.40
    繩
    0.40
     churn
    0.40
    POSITIVE LOGITS
    nyi
    0.47
     importanti
    0.47
    rī
    0.47
     muhimu
    0.46
    Tek
    0.46
    进展
    0.44
    ్రమ
    0.44
    ilization
    0.43
    叼
    0.43
     Usual
    0.43
    Activations Density 0.004%

    No Known Activations