© 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. 42575
    Prev
    Next
    INDEX
    Explanations

    the invention, Q:

    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
     ļoti
    -1.53
     izvē
    -1.41
     similar
    -1.40
     μας
    -1.38
     really
    -1.34
     mė
    -1.32
     mūsų
    -1.31
     ourselves
    -1.29
     fairly
    -1.29
     definitely
    -1.28
    POSITIVE LOGITS
    ͏
    1.50
    儚
    1.45
     nawet
    1.44
    咂
    1.42
    וּ
    1.42
    Награды
    1.41
     neuen
    1.40
    腼
    1.39
     бампер
    1.39
    expiresIn
    1.35
    Activations Density 0.000%

    No Known Activations