© 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. 34-GEMMASCOPE-RES-131K
    7. 109627
    Prev
    Next
    INDEX
    Explanations

    layout keywords

    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_34/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
    </h4>
    -1.27
    </h6>
    -1.23
    -1.11
    </h5>
    -1.09
    atória
    -1.02
     Trabalho
    -1.02
     kupa
    -0.98
     jao
    -0.98
    </h3>
    -0.95
    $}
    -0.95
    POSITIVE LOGITS
    ↵↵
    1.33
    你这
    0.94
     —
    0.90
     jusqu
    0.90
     intric
    0.89
     lă
    0.86
    accueil
    0.85
    Hanya
    0.83
    tablissements
    0.82
    ,'\
    0.81
    Activations Density 0.001%

    No Known Activations