© 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. 13477
    Prev
    Next
    INDEX
    Explanations

    my, tried, causing, show

    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
     balení
    -1.72
     Kasus
    -1.59
     saurait
    -1.49
     بنابراین
    -1.43
     komfor
    -1.39
    でしょうね
    -1.39
     Teknologi
    -1.38
    Additionally
    -1.37
     soñar
    -1.36
     poliuret
    -1.36
    POSITIVE LOGITS
     like
    1.88
     also
    1.55
    alties
    1.49
     they
    1.49
     different
    1.45
     them
    1.42
     not
    1.41
    :{
    1.41
     get
    1.38
     such
    1.38
    Activations Density 0.374%

    No Known Activations