© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14684
    Prev
    Next
    INDEX
    Explanations

    user input confirmation

    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_22/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
     also
    -1.57
     Geister
    -1.52
     similar
    -1.45
     jugend
    -1.42
     related
    -1.40
     its
    -1.34
     Hauptstadt
    -1.31
    !!!!!!
    -1.30
     Landschafts
    -1.30
     criteria
    -1.29
    POSITIVE LOGITS
    采用了
    1.36
    給你
    1.29
    系数
    1.18
     generalised
    1.16
    箭头
    1.16
    するので
    1.16
    分区
    1.16
    🧧
    1.16
    地圖
    1.13
    囑
    1.13
    Activations Density 0.009%

    No Known Activations