© 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. 10-GEMMASCOPE-RES-131K
    7. 21661
    Prev
    Next
    INDEX
    Explanations

    SQL WHERE clauses

    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_10/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
    </b>
    -1.65
     &
    -1.48
     one
    -1.47
     or
    -1.41
     ONE
    -1.38
     TWO
    -1.34
     F
    -1.33
     liksom
    -1.32
     for
    -1.30
     ifrån
    -1.30
    POSITIVE LOGITS
    selben
    1.60
     früheren
    1.57
     recentemente
    1.57
     justamente
    1.55
    ･･
    1.54
     Combien
    1.54
     우리
    1.53
     această
    1.52
     meditación
    1.52
     artesanato
    1.51
    Activations Density 0.022%

    No Known Activations