© 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. 22-GEMMASCOPE-RES-131K
    7. 104341
    Prev
    Next
    INDEX
    Explanations

    technical systems and programs

    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_22/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
     geométrico
    -1.10
     markiert
    -1.10
     anyone
    -1.09
     those
    -1.09
     OGSÅ
    -1.03
     encara
    -1.01
    ecute
    -1.00
     touched
    -1.00
    vedades
    -0.99
     белой
    -0.98
    POSITIVE LOGITS
    Глава
    1.23
    čni
    1.12
     itself
    1.05
     stanovnika
    1.01
    čna
    0.97
    ッピング
    0.96
    née
    0.96
    ció
    0.95
    čke
    0.95
     geometr
    0.90
    Activations Density 0.066%

    No Known Activations