© 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. 3555
    Prev
    Next
    INDEX
    Explanations

    or reconsider

    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
    still
    -0.81
    ᱩ
    -0.80
    always
    -0.80
     reinstatement
    -0.80
     デ
    -0.79
    mao
    -0.78
     reinstated
    -0.76
     задержа
    -0.75
    arbox
    -0.75
     changements
    -0.75
    POSITIVE LOGITS
     cut
    1.55
     exit
    1.32
     bail
    1.30
     terminate
    1.30
     terminates
    1.18
     walk
    1.14
     walked
    1.14
    cut
    1.09
     Exit
    1.06
    terminate
    1.06
    Activations Density 0.034%

    No Known Activations