© 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. 1550
    Prev
    Next
    INDEX
    Explanations

    X years old

    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
     the
    -2.06
    </b>
    -1.99
    さてさて
    -1.77
     recoge
    -1.73
    はどこ
    -1.71
    ーと
    -1.70
     caiu
    -1.70
     dubbed
    -1.69
    是因為
    -1.65
     può
    -1.60
    POSITIVE LOGITS
     gustaMe
    1.95
    无疑
    1.66
    ifying
    1.61
    葑
    1.55
    Kullan
    1.55
    其余
    1.55
    淬
    1.55
    これらの
    1.53
    性价比
    1.52
    鱺
    1.52
    Activations Density 0.018%

    No Known Activations