© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68962
    Prev
    Next
    INDEX
    Explanations

    ground floor retail, apartment, and amenities

    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
     szeptember
    -1.08
     augusztus
    -1.05
     afirmou
    -1.05
     dům
    -1.01
     március
    -1.00
     déploy
    -0.97
    demás
    -0.96
     február
    -0.95
     шокола
    -0.94
    tify
    -0.93
    POSITIVE LOGITS
     where
    1.38
     below
    1.13
    解放
    1.10
     basso
    1.06
     ground
    1.02
     comple
    0.94
     vse
    0.93
    paku
    0.93
     level
    0.92
    に戻
    0.92
    Activations Density 0.022%

    No Known Activations