© 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. 86785
    Prev
    Next
    INDEX
    Explanations

    naming things descriptively

    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
     intersper
    -0.93
     simpto
    -0.92
     cilind
    -0.91
    λες
    -0.91
     inond
    -0.89
    odziel
    -0.88
     instruk
    -0.87
    zili
    -0.87
    THA
    -0.85
     competente
    -0.84
    POSITIVE LOGITS
     descriptive
    1.69
     catchy
    1.65
     naming
    1.45
     name
    1.38
     Descriptive
    1.28
     branding
    1.27
     SEO
    1.25
    Descriptive
    1.23
    Naming
    1.22
     names
    1.17
    Activations Density 0.069%

    No Known Activations