© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66627
    Prev
    Next
    INDEX
    Explanations

    list of numbers

    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
     To
    -1.05
     without
    -1.05
     With
    -1.05
     It
    -0.98
     Both
    -0.94
     with
    -0.92
     womit
    -0.90
     During
    -0.90
    To
    -0.89
     by
    -0.88
    POSITIVE LOGITS
     rése
    1.11
    ズニー
    1.08
    艄
    1.05
    鯢
    1.05
    𓁹
    1.05
    臯
    1.04
    菒
    1.03
     kony
    1.02
     zodia
    1.02
     scarpe
    1.01
    Activations Density 0.066%

    No Known Activations