© 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. 83364
    Prev
    Next
    INDEX
    Explanations

    time-dependent evolution

    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
    Cycling
    -0.81
    vespa
    -0.77
    부
    -0.76
     Clarion
    -0.74
    薬
    -0.70
     vro
    -0.68
    käse
    -0.68
    CIRCLE
    -0.68
    İR
    -0.67
    Cricket
    -0.67
    POSITIVE LOGITS
     evolucion
    1.10
     domain
    1.05
     Domain
    1.04
     dependent
    0.96
     derivative
    0.96
     evolution
    0.96
    Dependent
    0.95
     steps
    0.90
     dependence
    0.86
     reversal
    0.83
    Activations Density 0.029%

    No Known Activations