© 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. 75256
    Prev
    Next
    INDEX
    Explanations

    field or fields

    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
    〜。
    -1.78
     schlechte
    -1.64
     leichte
    -1.63
     falsche
    -1.60
    ～。
    -1.58
    ᠂
    -1.57
    %")
    -1.56
     größere
    -1.56
    ・・。
    -1.55
    ate
    -1.55
    POSITIVE LOGITS
    ]
    1.90
    导弹
    1.66
     metropolitana
    1.62
     både
    1.59
     kegiatan
    1.57
    
    1.55
     सभी
    1.54
    雰
    1.52
    rechter
    1.49
    >
    1.48
    Activations Density 0.072%

    No Known Activations