© 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. 62743
    Prev
    Next
    INDEX
    Explanations

    state after completion

    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
    Not in Any Lists

    No Comments

    Negative Logits
     actuellement
    -1.18
     many
    -1.16
     langsung
    -1.16
     while
    -1.09
     Anlass
    -1.06
     when
    -1.05
     stories
    -1.05
     before
    -1.05
     INFORMACIÓN
    -1.03
    っていたので
    -1.03
    POSITIVE LOGITS
     satisfactorily
    2.06
     satisfactory
    1.87
     sufficiently
    1.64
     xong
    1.42
     successfully
    1.37
     prelimin
    1.34
     agreeable
    1.28
     sufficient
    1.28
     adequately
    1.17
    初步
    1.16
    Activations Density 0.055%

    No Known Activations