© 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. 22-GEMMASCOPE-RES-131K
    7. 13624
    Prev
    Next
    INDEX
    Explanations

    Sieve of Eratosthenes

    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_22/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
     pestañas
    -1.04
     freddo
    -1.02
    Ɲ
    -0.99
     byd
    -0.98
    JSON
    -0.96
    vezet
    -0.93
    /}
    -0.92
    voyez
    -0.92
    <td>
    -0.92
     konfig
    -0.92
    POSITIVE LOGITS
    <bos>
    1.07
    箕
    1.00
    atá
    0.95
    Popis
    0.94
     Alltag
    0.91
     today
    0.90
    ciata
    0.90
     thereafter
    0.90
    宝物
    0.88
     hauptsächlich
    0.88
    Activations Density 0.003%

    No Known Activations