© 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. 70983
    Prev
    Next
    INDEX
    Explanations

    joining lists

    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
    為に
    -1.66
    racked
    -1.43
     trám
    -1.35
     dinoss
    -1.26
     dezelve
    -1.25
    昨日の
    -1.25
     cejas
    -1.24
     verwijderen
    -1.20
    lament
    -1.20
    んですね
    -1.20
    POSITIVE LOGITS
     other
    1.76
    などの
    1.61
     have
    1.57
     Außerdem
    1.45
     by
    1.45
    などを
    1.37
    があり
    1.36
     has
    1.35
     nonché
    1.33
     possess
    1.30
    Activations Density 0.103%

    No Known Activations