© 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. 115442
    Prev
    Next
    INDEX
    Explanations

    number words

    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
     menit
    -0.85
     frec
    -0.85
    entikan
    -0.84
     Mejía
    -0.83
    lès
    -0.83
    ТС
    -0.83
     detik
    -0.81
     litri
    -0.81
     particolar
    -0.81
     thous
    -0.80
    POSITIVE LOGITS
     twenty
    1.19
     Forty
    1.11
     forty
    1.07
     thirty
    1.05
     Twenty
    0.99
     fifty
    0.98
    ۳۰
    0.96
     большо
    0.93
     Thirty
    0.92
     большого
    0.91
    Activations Density 0.013%

    No Known Activations