© 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. 22-GEMMASCOPE-RES-131K
    7. 32742
    Prev
    Next
    INDEX
    Explanations

    numbered lists or bullet points

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    内置
    -0.99
     字母
    -0.91
     (--
    -0.91
     certe
    -0.85
    𝙜
    -0.85
    おわりに
    -0.85
     certain
    -0.84
     Ι
    -0.83
     they
    -0.83
     Cached
    -0.82
    POSITIVE LOGITS
    2
    0.97
    8
    0.93
    3
    0.92
    ²(
    0.92
    5
    0.90
    ↵↵↵
    0.86
     kılıf
    0.84
     galima
    0.84
     embalaje
    0.83
    eksi
    0.83
    Activations Density 0.173%

    No Known Activations