© 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. 45414
    Prev
    Next
    INDEX
    Explanations

    identify and characterize

    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
    Not in Any Lists

    No Comments

    Negative Logits
     she
    -1.69
     для
    -1.69
     برای
    -1.59
    2
    -1.56
    €™
    -1.52
    ztes
    -1.51
     to
    -1.48
    €“
    -1.41
     my
    -1.41
    嘿嘿
    -1.41
    POSITIVE LOGITS
    AZIONE
    1.75
     nke
    1.63
     kwamba
    1.60
     giorgio
    1.60
     paff
    1.54
     aveo
    1.51
     santana
    1.49
     daewoo
    1.49
     yves
    1.46
     roberto
    1.45
    Activations Density 0.047%

    No Known Activations