© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83777
    Prev
    Next
    INDEX
    Explanations

    speed and quickness

    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
    Negative Logits
     natomiast
    -1.22
     pocas
    -1.22
    奋斗
    -1.21
     showcased
    -1.19
     clín
    -1.17
    どういう
    -1.17
    s
    -1.16
     geomé
    -1.16
     no
    -1.14
    少なく
    -1.10
    POSITIVE LOGITS
    ógicas
    1.46
    »?
    1.46
    錾
    1.45
    豋
    1.45
    msford
    1.45
     Inſ
    1.43
    原神
    1.41
    จะ
    1.40
     expédi
    1.38
     作り方
    1.38
    Activations Density 0.110%

    No Known Activations