© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32425
    Prev
    Next
    INDEX
    Explanations

    citations like [[@B...]] or [[@CR...]]

    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
    ktop
    -1.22
     everything
    -1.05
    Still
    -1.02
     still
    -0.98
     Hòa
    -0.98
    тим
    -0.95
    <0xEF>
    -0.95
    häuse
    -0.95
    vertebrates
    -0.92
    
    -0.92
    POSITIVE LOGITS
    la
    1.02
    il
    1.00
    rl
    0.94
    p
    0.89
     чаще
    0.87
     comienzos
    0.87
     zahlreichen
    0.86
    u
    0.85
    r
    0.85
    lo
    0.85
    Activations Density 0.013%

    No Known Activations