© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74253
    Prev
    Next
    INDEX
    Explanations

    none

    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
     estadounid
    -1.95
    甞
    -1.90
     was
    -1.84
    etzten
    -1.84
     手绘
    -1.83
    这般
    -1.82
    ölcs
    -1.78
     विश्वसनीय
    -1.76
     semacam
    -1.73
     Auffassung
    -1.69
    POSITIVE LOGITS
    蔟
    1.98
    ☫
    1.88
    n
    1.78
    蛋白
    1.68
    nolia
    1.67
    荅
    1.65
    的呢
    1.64
     —
    1.64
     []:
    1.63
     of
    1.61
    Activations Density 0.011%

    No Known Activations