© 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. 39834
    Prev
    Next
    INDEX
    Explanations

    reasoning framework

    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
     indicó
    -1.59
     randonnée
    -1.49
     творо
    -1.47
     detalló
    -1.45
     аромат
    -1.45
     cojín
    -1.41
     Reised
    -1.37
     витами
    -1.35
    ſſion
    -1.32
    Associazione
    -1.31
    POSITIVE LOGITS
    ֠
    1.91
     cristianismo
    1.75
     掃除
    1.73
     вѣ
    1.64
     дѣ
    1.59
     Theologie
    1.59
     встроен
    1.51
    рѣ
    1.49
     мона
    1.48
     экрана
    1.47
    Activations Density 0.038%

    No Known Activations