© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2215
    Prev
    Next
    INDEX
    Explanations

    news sources and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鬯
    0.50
     ২০১৫
    0.49
    铨
    0.48
    Coref
    0.47
     Ontology
    0.43
     Solubility
    0.42
     ২০১৩
    0.42
    兖
    0.42
     Bioinformatics
    0.41
     Tumblr
    0.41
    POSITIVE LOGITS
    Reuters
    1.01
     Reuters
    1.00
    CNN
    0.93
     CNN
    0.91
    BBC
    0.85
     BBC
    0.82
     CNBC
    0.79
    cnn
    0.74
     Bloomberg
    0.73
    Bloomberg
    0.70
    Activations Density 0.125%

    No Known Activations