© 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. 102136
    Prev
    Next
    INDEX
    Explanations

    CicLAvia, CIC, Cicer

    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
     is
    -2.84
    
    -2.33
    racite
    -2.30
    心头
    -2.30
    想了想
    -2.27
    for
    -2.25
    稣
    -2.17
    を選択
    -2.16
     OUR
    -2.14
    栒
    -2.14
    POSITIVE LOGITS
    是
    2.88
     мои
    2.41
    }
    2.38
    '
    2.33
    ﮑ
    2.30
     แล้ว
    2.27
    ia
    2.27
     längere
    2.25
    Kenapa
    2.17
    ':
    2.13
    Activations Density 0.008%

    No Known Activations