© 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. 62619
    Prev
    Next
    INDEX
    Explanations

    counting zero, one, two

    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
    iega
    -1.06
     apostar
    -1.03
     of
    -1.03
     пев
    -0.96
     around
    -0.96
     said
    -0.93
     with
    -0.93
     about
    -0.91
    نویس
    -0.91
    médiaire
    -0.91
    POSITIVE LOGITS
    ateness
    1.00
     tane
    0.98
    itself
    0.98
    xffff
    0.96
    いため
    0.93
    ️⃣
    0.91
    moiselle
    0.91
    ſt
    0.91
    throughout
    0.91
    嚥
    0.91
    Activations Density 0.132%

    No Known Activations