© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100500
    Prev
    Next
    INDEX
    Explanations

    non-english characters or words

    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
    </i>
    -2.09
    ϰ
    -2.05
    -
    -2.05
    ครื่อง
    -1.98
     Importantly
    -1.92
    .'
    -1.91
     esboço
    -1.90
    鼉
    -1.84
    你不要
    -1.84
    archiwizowane
    -1.84
    POSITIVE LOGITS
     or
    2.47
    彿
    1.87
    acaktır
    1.81
     warmen
    1.70
     would
    1.69
    姆
    1.68
     competitivo
    1.65
    ↵↵
    1.65
    刺客
    1.64
     psicológico
    1.63
    Activations Density 0.005%

    No Known Activations