© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67657
    Prev
    Next
    INDEX
    Explanations

    recent, latest, or featured items

    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
     koš
    -1.27
    комплект
    -1.24
     žal
    -1.09
     августа
    -1.06
    ついて
    -1.05
     when
    -1.05
     Générale
    -1.05
    imetry
    -1.02
    ülerin
    -1.02
     enfrentan
    -0.99
    POSITIVE LOGITS
     ベージュ
    1.30
     destacados
    1.18
     ネイビー
    1.13
    一辆
    1.06
    arana
    1.05
    悻
    1.05
    このように
    1.05
    撂
    1.05
     news
    1.04
     sortes
    1.04
    Activations Density 0.029%

    No Known Activations