© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70600
    Prev
    Next
    INDEX
    Explanations

    retreat

    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
    鴴
    -2.52
    ઁ
    -2.50
    ឵
    -2.44
     男人
    -2.42
    同様に
    -2.27
    籮
    -2.23
    同様
    -2.22
    ta
    -2.22
     rád
    -2.20
    ネットで
    -2.20
    POSITIVE LOGITS
    ↵
    2.95
    有
    2.78
     They
    2.64
     schonmal
    2.55
    一定的
    2.44
    ,”
    2.33
    如果
    2.33
    芣
    2.27
    さん
    2.22
    筚
    2.20
    Activations Density 0.001%

    No Known Activations