© 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. 48319
    Prev
    Next
    INDEX
    Explanations

    organize information and lists

    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
    elding
    -1.75
    utdown
    -1.62
     Añade
    -1.61
    雱
    -1.59
     --
    -1.58
     gekenn
    -1.58
     gemessen
    -1.55
     erwäh
    -1.55
     ausdrück
    -1.55
     bewertet
    -1.53
    POSITIVE LOGITS
    çons
    1.57
    蛧
    1.55
     which
    1.52
    ção
    1.52
    !’
    1.51
    カウン
    1.50
     perte
    1.48
    ag
    1.48
    芣
    1.48
     QUÉ
    1.47
    Activations Density 0.036%

    No Known Activations