© 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. 34-GEMMASCOPE-RES-131K
    4. 84230
    Prev
    Next
    INDEX
    Explanations

    license text, copyright notices

    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_34/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
     Klo
    -0.75
    航
    -0.70
     equalization
    -0.68
    favorited
    -0.67
    的多
    -0.67
    zeczytaj
    -0.66
    (""+
    -0.64
     chords
    -0.64
     Lotto
    -0.63
     ecu
    -0.62
    POSITIVE LOGITS
     Biophys
    0.73
    んですが
    0.72
    atifs
    0.71
    有個
    0.69
     zmar
    0.68
    謔
    0.68
    いため
    0.67
    chafter
    0.67
     Grazie
    0.65
    Ǟ
    0.65
    Activations Density 0.064%

    No Known Activations