© 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. 22-GEMMASCOPE-RES-131K
    7. 70799
    Prev
    Next
    INDEX
    Explanations

    peer review

    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_22/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
    ↵↵
    -2.92
     ‘
    -2.81
     he
    -2.48
     “
    -2.34
    -2.30
     introduce
    -2.28
     has
    -2.25
    と言えば
    -2.20
     is
    -2.19
     don
    -2.14
    POSITIVE LOGITS
    ㍑
    2.94
     anhänger
    2.83
    
    2.75
     jepang
    2.73
    鉿
    2.67
     rajut
    2.64
    螄
    2.63
     miniaturka
    2.63
    毉
    2.61
    うわ
    2.59
    Activations Density 0.004%

    No Known Activations