© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107840
    Prev
    Next
    INDEX
    Explanations

    higher, larger, bigger, smaller, greater

    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
    instead
    -1.12
    歺
    -0.98
    шаго
    -0.98
     futu
    -0.97
     มิ
    -0.92
     praticamente
    -0.92
    软件特色
    -0.91
     Selle
    -0.90
    ఝ
    -0.90
     revan
    -0.90
    POSITIVE LOGITS
     higher
    3.84
     larger
    3.22
     bigger
    2.92
     smaller
    2.80
     greater
    2.61
     increasing
    2.52
     lower
    2.47
    higher
    2.45
     increased
    2.45
     Higher
    2.44
    Activations Density 0.128%

    No Known Activations