© 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. 12436
    Prev
    Next
    INDEX
    Explanations

    for loops with incrementing i

    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
     parachoque
    -1.13
     zwem
    -1.13
     volledige
    -1.02
     mortes
    -1.00
     srd
    -0.99
     zomer
    -0.96
    rovna
    -0.96
    celotti
    -0.95
     Issus
    -0.93
     persoonlijke
    -0.93
    POSITIVE LOGITS
     it
    1.21
     feiner
    1.06
     important
    0.96
    它們
    0.90
     I
    0.90
     organisms
    0.89
    一分
    0.88
     different
    0.87
    ↵
    0.87
    把它
    0.87
    Activations Density 0.003%

    No Known Activations