© 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. 32955
    Prev
    Next
    INDEX
    Explanations

    opening new locations or branches

    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
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -1.59
     nevera
    -1.11
     for
    -1.11
    さんが
    -1.08
     sometimes
    -1.03
     cioc
    -1.01
     الذي
    -1.00
     Gastgeber
    -0.98
     ingredientes
    -0.94
    getOut
    -0.94
    POSITIVE LOGITS
     expansion
    1.60
    Expansion
    1.42
     locations
    1.38
     expansions
    1.38
     Expansion
    1.27
     expand
    1.27
     expandir
    1.22
     расши
    1.20
    expansion
    1.18
     Adicion
    1.14
    Activations Density 0.025%

    No Known Activations