© 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. 49598
    Prev
    Next
    INDEX
    Explanations

    quantitative analysis and methods

    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
    STRUCTION
    -1.09
    Proble
    -0.96
     wo
    -0.94
     hapless
    -0.94
    anthony
    -0.90
     gekennzeichnet
    -0.87
     gött
    -0.86
    niv
    -0.86
     Avoiding
    -0.85
     éstos
    -0.85
    POSITIVE LOGITS
     analysis
    1.28
     methods
    1.18
     changes
    1.11
     aspects
    1.02
     approaches
    1.02
     easing
    1.01
     assessment
    0.98
     assessing
    0.95
     METHODS
    0.94
    methods
    0.93
    Activations Density 0.038%

    No Known Activations