© 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. 10-GEMMASCOPE-RES-131K
    7. 19163
    Prev
    Next
    INDEX
    Explanations

    phrases followed by of

    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_10/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
    鼷
    -2.63
    íg
    -2.20
    我们需要
    -2.19
    
    -2.17
    蚡
    -2.17
    他们是
    -2.06
    馘
    -2.06
    Ꮻ
    -2.06
    腘
    -2.05
    月から
    -2.03
    POSITIVE LOGITS
     of
    3.33
     he
    2.41
    I
    2.36
    A
    2.08
     Significantly
    1.97
     serán
    1.92
     Earlier
    1.92
     they
    1.91
    窳
    1.88
     "";
    1.88
    Activations Density 0.004%

    No Known Activations