© 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. 84455
    Prev
    Next
    INDEX
    Explanations

    depth 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_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
    书签
    -1.02
     There
    -0.88
    上品
    -0.88
     なら
    -0.87
    
    -0.87
     faldas
    -0.85
     passenden
    -0.85
     halben
    -0.84
    Що
    -0.84
     thing
    -0.83
    POSITIVE LOGITS
     Depth
    1.62
     depth
    1.49
    Depth
    1.36
     深
    1.34
    depth
    1.34
     pero
    1.22
     DEPTH
    1.20
     of
    1.16
     perception
    1.13
    Stencil
    1.11
    Activations Density 0.010%

    No Known Activations