© 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. 56867
    Prev
    Next
    INDEX
    Explanations

    numbers following punctuation

    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
    йн
    -0.79
    蘇
    -0.79
     Sgt
    -0.76
    Sgt
    -0.74
    苏
    -0.73
     др
    -0.73
    Invitrogen
    -0.72
    бель
    -0.71
    Eq
    -0.71
     Eq
    -0.70
    POSITIVE LOGITS
     ninety
    1.19
     seventy
    1.17
     eighty
    1.16
     nineteenth
    1.06
    twenty
    1.03
     twenty
    1.03
    fifty
    1.02
     thirty
    0.98
     thirteenth
    0.98
     fifty
    0.97
    Activations Density 0.141%

    No Known Activations