© 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. 72869
    Prev
    Next
    INDEX
    Explanations

    json manipulation

    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
     They
    -3.02
    h
    -2.97
    </i>
    -2.81
    ).
    -2.77
    ↵↵
    -2.59
    }$,
    -2.55
     selben
    -2.52
    -2.48
    ’
    -2.44
    呖
    -2.39
    POSITIVE LOGITS
    过去的
    2.44
    我这
    2.42
     rústico
    2.42
     decorativo
    2.34
    当时的
    2.33
    昔の
    2.25
     nativo
    2.25
    hasilkan
    2.22
     \
    2.22
     може
    2.19
    Activations Density 0.013%

    No Known Activations