© 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. 10-GEMMASCOPE-RES-131K
    4. 99574
    Prev
    Next
    INDEX
    Explanations

    issues, problems, or concerns

    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
     that
    -1.77
    henswürdigkeiten
    -1.49
     사람
    -1.45
     Presumably
    -1.41
     面包
    -1.41
     evidentemente
    -1.39
    iramente
    -1.38
     Then
    -1.38
     котором
    -1.37
    </h3>
    -1.32
    POSITIVE LOGITS
     if
    2.17
     and
    2.05
     or
    1.88
     also
    1.75
    还是要
    1.63
     sobě
    1.56
     doble
    1.56
     jika
    1.54
     grote
    1.51
     matriz
    1.48
    Activations Density 0.193%

    No Known Activations