© 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. 61484
    Prev
    Next
    INDEX
    Explanations

    code function calls and returns

    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
     that
    -1.92
     utiliser
    -1.77
    珦
    -1.52
     these
    -1.52
     whom
    -1.41
     sicherzustellen
    -1.41
     selalu
    -1.40
    すぎた
    -1.40
     ameryka
    -1.39
    翆
    -1.39
    POSITIVE LOGITS
     it
    1.74
     there
    1.33
    我的
    1.32
    رم
    1.31
    atigable
    1.30
    まずは
    1.28
    它
    1.26
     one
    1.24
    itisation
    1.18
    login
    1.17
    Activations Density 0.032%

    No Known Activations