© 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. 73576
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code

    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
    مقاله
    -0.98
    jść
    -0.97
     probablement
    -0.96
     trochę
    -0.93
     Ngoài
    -0.93
    こんな感じで
    -0.93
    為に
    -0.90
     pédagog
    -0.90
    Kesimpulan
    -0.88
    Demikian
    -0.87
    POSITIVE LOGITS
    ㅤ
    0.93
     выбирать
    0.91
    mCamera
    0.91
    <s>
    0.88
    ciado
    0.88
    told
    0.87
    terness
    0.87
    cising
    0.86
    cised
    0.86
    ruptedException
    0.86
    Activations Density 0.001%

    No Known Activations