© 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. 130720
    Prev
    Next
    INDEX
    Explanations

    poor [noun describing deficiency]

    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
    щал
    -1.66
    徬
    -1.65
    嫉
    -1.65
    XXIV
    -1.64
    Ensuite
    -1.61
     dificultades
    -1.59
     asfal
    -1.58
     प्रत्येक
    -1.57
    ṉ
    -1.57
    すでに
    -1.55
    POSITIVE LOGITS
    3
    1.96
    8
    1.85
    2
    1.82
     it
    1.66
    7
    1.59
    t
    1.49
     in
    1.49
    一
    1.47
     スタ
    1.45
    How
    1.43
    Activations Density 0.024%

    No Known Activations