© 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. 6677
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
     There
    -1.59
     It
    -1.56
     We
    -1.48
    縝
    -1.38
    のようです
    -1.36
     According
    -1.34
     As
    -1.33
     Several
    -1.33
     to
    -1.32
     Although
    -1.32
    POSITIVE LOGITS
     pleaf
    1.74
     perfons
    1.55
     fufficient
    1.43
     firft
    1.43
     fhort
    1.41
    ENED
    1.39
    still
    1.38
    🛇
    1.38
     falda
    1.37
     poffe
    1.35
    Activations Density 0.063%

    No Known Activations