© 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. 56106
    Prev
    Next
    INDEX
    Explanations

    code, timestamps, mathematics

    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
    Срок
    -0.81
    ἴ
    -0.75
     ίδ
    -0.73
    ﷽
    -0.71
     snapped
    -0.71
    Posting
    -0.71
     вот
    -0.71
     Posting
    -0.70
    тельном
    -0.70
    ままで
    -0.70
    POSITIVE LOGITS
     louer
    0.81
     Sandoval
    0.75
    ANOVA
    0.72
    ο
    0.71
    Figs
    0.70
    {$\
    0.70
     ANOVA
    0.70
    ORAL
    0.70
    mondo
    0.69
     FACULTY
    0.69
    Activations Density 0.091%

    No Known Activations