© 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. 715
    Prev
    Next
    INDEX
    Explanations

    anonymous tips

    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
     for
    -1.35
     when
    -0.91
    SALUD
    -0.91
    批准
    -0.91
     väli
    -0.88
    Kích
    -0.88
    Karakteristik
    -0.86
    Сколько
    -0.85
    ejemplo
    -0.84
     ibang
    -0.83
    POSITIVE LOGITS
     contact
    1.55
    contact
    1.41
    Contact
    1.30
     anonymously
    1.09
     anonymous
    1.08
     call
    1.07
     Contact
    1.05
    Tip
    1.04
     tip
    1.03
     tips
    1.02
    Activations Density 0.004%

    No Known Activations