© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79287
    Prev
    Next
    INDEX
    Explanations

    checking instance type

    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
     卵
    -0.83
    dialement
    -0.80
    Noter
    -0.79
    注解
    -0.79
    ρισσότε
    -0.77
    ūsu
    -0.77
    chê
    -0.76
     Toibin
    -0.75
    loč
    -0.75
    ené
    -0.74
    POSITIVE LOGITS
     instanceof
    4.44
     isinstance
    3.03
    InstanceOf
    2.27
    isinstance
    2.23
     instance
    2.16
    instance
    2.09
     isKindOfClass
    1.96
     INSTANCE
    1.45
     Instance
    1.41
     instances
    1.30
    Activations Density 0.018%

    No Known Activations