© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13968
    Prev
    Next
    INDEX
    Explanations

    However

    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
    我们
    -0.91
    之间
    -0.89
    ordu
    -0.85
     vermelhas
    -0.82
    uldade
    -0.79
     statistique
    -0.79
     potentially
    -0.79
     bä
    -0.78
    anın
    -0.77
    ♑
    -0.76
    POSITIVE LOGITS
    地说道
    0.91
    吮
    0.90
    รรม
    0.89
    …~
    0.87
     jane
    0.86
     [/
    0.85
     выясни
    0.84
     '?'
    0.82
    niki
    0.81
     mentre
    0.81
    Activations Density 0.201%

    No Known Activations