© 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. 10-GEMMASCOPE-RES-131K
    7. 20381
    Prev
    Next
    INDEX
    Explanations

    alphabetic letter or characters

    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_10/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
     одну
    -2.25
    cheme
    -1.95
    eee
    -1.87
    M
    -1.83
    datable
    -1.82
    thirds
    -1.80
     ouver
    -1.80
    abilities
    -1.79
    RE
    -1.78
    itisation
    -1.77
    POSITIVE LOGITS
     That
    2.20
     Encuentra
    1.91
     we
    1.86
     становится
    1.81
     Our
    1.76
     habrá
    1.75
    ᗯ
    1.74
     Let
    1.73
     will
    1.72
    ریق
    1.71
    Activations Density 0.014%

    No Known Activations