© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113255
    Prev
    Next
    INDEX
    Explanations

    too much or too little

    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_10/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
     VERY
    -1.72
     utilisent
    -1.65
    ,
    -1.62
    挹
    -1.48
    probably
    -1.45
    离开了
    -1.43
     Ý
    -1.42
     butik
    -1.42
    瞇
    -1.40
    唏
    -1.39
    POSITIVE LOGITS
     now
    1.95
     or
    1.86
     their
    1.70
     terlalu
    1.66
     especially
    1.65
     too
    1.59
     which
    1.59
     while
    1.55
     on
    1.47
     allowing
    1.45
    Activations Density 0.054%

    No Known Activations