© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    straightforward and clear

    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
     ára
    -0.80
    Werner
    -0.79
     verdade
    -0.78
    Welsh
    -0.73
    strains
    -0.73
    izzare
    -0.72
    oustic
    -0.72
    variants
    -0.71
     Welsh
    -0.70
     üst
    -0.69
    POSITIVE LOGITS
     straightforward
    3.25
     cut
    2.64
    cut
    2.41
     clear
    2.20
    straight
    2.05
     straight
    1.98
    Cut
    1.93
     simple
    1.90
    clear
    1.90
     Cut
    1.83
    Activations Density 0.049%

    No Known Activations