© 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. 28279
    Prev
    Next
    INDEX
    Explanations

    mouse click or drag

    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
    kaç
    -0.98
    严重的
    -0.97
    ᜀ
    -0.97
    Филь
    -0.96
    Businesses
    -0.96
     ]);
    -0.94
    Budapest
    -0.93
    Kelas
    -0.93
     desfile
    -0.93
    Ранее
    -0.93
    POSITIVE LOGITS
     by
    1.14
     click
    1.13
     mouse
    0.98
     hand
    0.96
     press
    0.95
     they
    0.93
     with
    0.93
     actitudes
    0.88
     cambiar
    0.88
     два
    0.88
    Activations Density 0.018%

    No Known Activations