© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70416
    Prev
    Next
    INDEX
    Explanations

    do with or away

    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
     protestas
    -1.91
     baskılı
    -1.89
    呟
    -1.83
    渽
    -1.81
    鸸
    -1.77
    紆
    -1.77
    ſſen
    -1.73
    おまけ
    -1.71
     condicionado
    -1.68
    一旁的
    -1.65
    POSITIVE LOGITS
    7
    2.00
    for
    1.93
    5
    1.84
    8
    1.78
    4
    1.77
     need
    1.69
    US
    1.65
    9
    1.61
     Tetapi
    1.60
    این
    1.58
    Activations Density 0.004%

    No Known Activations