© 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. 42656
    Prev
    Next
    INDEX
    Explanations

    one 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
     there
    -1.38
    ☆☆☆☆☆
    -1.36
    ^_^
    -1.26
    IDADE
    -1.23
     acide
    -1.22
    Hrs
    -1.22
    **/
    -1.22
     余
    -1.21
    rium
    -1.19
     secondes
    -1.19
    POSITIVE LOGITS
     Another
    1.58
     his
    1.53
    大概是
    1.52
    要把
    1.47
    差不多
    1.46
    人和
    1.45
      
    1.45
     Also
    1.44
    全是
    1.43
     podría
    1.40
    Activations Density 0.051%

    No Known Activations