© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64855
    Prev
    Next
    INDEX
    Explanations

    legal and licensing information

    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
     tempi
    -0.79
    XXXX
    -0.77
    =_
    -0.75
     espectáculo
    -0.75
     becomes
    -0.74
     InputDecoration
    -0.73
     to
    -0.73
     soggetto
    -0.72
    بير
    -0.71
     dağı
    -0.71
    POSITIVE LOGITS
     CROSS
    1.52
     cross
    1.48
    cross
    1.44
    CROSS
    1.33
    Cross
    1.28
     Cross
    1.23
    crossing
    1.14
    crossed
    1.13
     crossover
    1.05
     crossed
    1.02
    Activations Density 0.004%

    No Known Activations