© 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. 45735
    Prev
    Next
    INDEX
    Explanations

    identifiers followed by underscore

    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
     will
    -2.16
     different
    -1.98
     greatly
    -1.97
     changed
    -1.97
     strangely
    -1.91
     incredible
    -1.88
     showed
    -1.88
     relatively
    -1.84
     completely
    -1.82
     things
    -1.81
    POSITIVE LOGITS
     of
    3.42
     anunció
    2.25
    .
    2.09
    btw
    1.94
    provides
    1.94
     verhind
    1.92
     nieuwe
    1.88
    providing
    1.87
    honestly
    1.83
     dobry
    1.82
    Activations Density 0.169%

    No Known Activations