© 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. 103903
    Prev
    Next
    INDEX
    Explanations

    guest access or code definitions

    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
    
    -1.07
     devlet
    -1.01
     daban
    -0.96
     ölüm
    -0.94
    vated
    -0.93
    cibility
    -0.92
    ⎓
    -0.92
     Französ
    -0.92
     öld
    -0.91
     më
    -0.91
    POSITIVE LOGITS
     LOCATION
    1.01
    //
    0.96
    Location
    0.91
     docking
    0.87
     dock
    0.87
    Dock
    0.85
     –
    0.85
    e
    0.84
     derselben
    0.84
    ebly
    0.84
    Activations Density 0.001%

    No Known Activations