© 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. 34-GEMMASCOPE-RES-131K
    7. 56804
    Prev
    Next
    INDEX
    Explanations

    Are you (question)?

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     your
    -1.50
     you
    -1.09
     justo
    -1.06
    ()]
    -1.05
     Your
    -1.01
    ätigung
    -1.01
     pokaz
    -1.01
     tuoi
    -1.00
    ondheim
    -0.98
    İstin
    -0.96
    POSITIVE LOGITS
     sure
    2.00
     aware
    1.45
    sure
    1.43
     guys
    1.40
     still
    1.35
     kidding
    1.33
    Sure
    1.26
    确定
    1.09
     there
    1.04
     SURE
    1.04
    Activations Density 0.010%

    No Known Activations