© 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. 24910
    Prev
    Next
    INDEX
    Explanations

    software keywords

    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
    1
    -1.20
     this
    -1.16
     Dispon
    -1.13
     from
    -1.10
     korban
    -1.06
     diskusi
    -1.06
     terapi
    -1.05
     some
    -1.05
     diras
    -1.04
     if
    -1.02
    POSITIVE LOGITS
    excellents
    1.35
    ≅
    1.22
    𝟏
    1.21
    ₱
    1.17
     ilman
    1.16
     учета
    1.13
    ٣
    1.13
    ışı
    1.13
    eterangan
    1.11
     Code
    1.10
    Activations Density 0.007%

    No Known Activations