© 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. 60809
    Prev
    Next
    INDEX
    Explanations

    new programs and features

    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
     memoized
    -0.88
    Celebrating
    -0.85
     BREAKING
    -0.83
    Alp
    -0.82
    Obfuscated
    -0.82
     Hern
    -0.79
     outlier
    -0.79
    NLP
    -0.79
     nasel
    -0.79
     Middleware
    -0.78
    POSITIVE LOGITS
     Secure
    1.05
     My
    1.04
     Quick
    1.02
     Connect
    1.02
     their
    1.01
     Smart
    0.99
     initiatives
    0.93
     Create
    0.90
     mahdollis
    0.89
     True
    0.89
    Activations Density 0.106%

    No Known Activations