© 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. 34-GEMMASCOPE-RES-131K
    7. 107324
    Prev
    Next
    INDEX
    Explanations

    share this post email this article

    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
     its
    -1.02
     cikin
    -0.92
     variations
    -0.88
     VARI
    -0.84
     puisqu
    -0.80
    measuring
    -0.80
     Bakar
    -0.80
    variation
    -0.80
     fonctionner
    -0.79
    Variation
    -0.78
    POSITIVE LOGITS
     flowers
    1.21
     tingkat
    0.94
     expr
    0.93
     seorang
    0.89
    =\"
    0.86
    leyebilirsiniz
    0.84
    cence
    0.84
    LOAT
    0.83
    Flowers
    0.82
     Lokasi
    0.82
    Activations Density 0.002%

    No Known Activations