© 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. 34-GEMMASCOPE-RES-131K
    7. 102368
    Prev
    Next
    INDEX
    Explanations

    software usability and functionality

    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_34/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
    endront
    -1.20
    Wikimedia
    -1.10
     möglicherweise
    -1.10
    常見
    -1.08
    eschouwers
    -1.06
     подходя
    -1.05
    FlatButton
    -1.05
     Chrif
    -1.05
     regulations
    -1.04
    PushMatrix
    -1.01
    POSITIVE LOGITS
     workflow
    1.59
     usability
    1.53
     functionality
    1.39
     workflows
    1.28
     user
    1.24
     use
    1.24
    使い
    1.23
    productivity
    1.21
     productivity
    1.18
     functions
    1.14
    Activations Density 0.193%

    No Known Activations