© 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. 296
    Prev
    Next
    INDEX
    Explanations

    connects phrases with words

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

    analysis and exploration

    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
     abortions
    0.22
     housework
    0.20
     үч
    0.20
    4
    0.19
    ４
    0.19
     four
    0.18
     blames
    0.18
    。
    0.18
     murdering
    0.18
     suing
    0.18
    POSITIVE LOGITS
    无论是
    0.21
     י
    0.19
    immers
    0.19
     elucid
    0.19
    ostante
    0.19
     ensure
    0.18
    展现
    0.18
     अद्वितीय
    0.18
    𒅌
    0.18
     প্রত
    0.18
    Activations Density 0.074%

    No Known Activations