© 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. 36488
    Prev
    Next
    INDEX
    Explanations

    month day year or abbreviation

    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
    vka
    -0.98
    diens
    -0.97
     déjà
    -0.93
    因而
    -0.88
     Puedes
    -0.88
     результате
    -0.88
     usual
    -0.87
    huit
    -0.87
    氏の
    -0.85
    ttps
    -0.85
    POSITIVE LOGITS
    初代
    0.96
     this
    0.91
    dö
    0.90
     vertes
    0.85
    rabh
    0.84
    瑧
    0.84
    ▂
    0.83
    ㄣ
    0.83
    ětí
    0.83
     just
    0.83
    Activations Density 0.010%

    No Known Activations