© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93706
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    想的
    -0.91
     сказа
    -0.87
    MEDIUM
    -0.82
    ännande
    -0.80
     arrayOf
    -0.79
     السعود
    -0.77
    ずっと
    -0.73
     dimulai
    -0.70
    FRAGMENT
    -0.70
    セット
    -0.70
    POSITIVE LOGITS
    },{
    
    0.78
     nærm
    0.75
     segmentos
    0.74
    🦴
    0.71
    ЦИИ
    0.71
    AA
    0.71
     acheteurs
    0.71
     aa
    0.71
    ą
    0.71
     białym
    0.69
    Activations Density 0.011%

    No Known Activations