© 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. 105968
    Prev
    Next
    INDEX
    Explanations

    Good

    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
    饧
    -1.87
    쫀
    -1.73
     deterioro
    -1.73
    だら
    -1.70
     nombreuses
    -1.67
     neuesten
    -1.65
     景点
    -1.63
    ほんとに
    -1.59
    等我
    -1.59
    𐀀
    -1.58
    POSITIVE LOGITS
    árez
    1.59
    晔
    1.55
     epitom
    1.55
     insisted
    1.53
     seems
    1.47
    wają
    1.46
    {{-
    1.45
     seemed
    1.45
    hoka
    1.44
    尼
    1.39
    Activations Density 0.008%

    No Known Activations