© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64576
    Prev
    Next
    INDEX
    Explanations

    Bal at the beginning of 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_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
    ！」
    -0.74
     conducted
    -0.71
    運命
    -0.70
    絵
    -0.69
    轻松
    -0.69
     offline
    -0.68
     prisma
    -0.68
    清潔
    -0.67
    写真は
    -0.66
    建築
    -0.66
    POSITIVE LOGITS
     Bal
    1.36
     bal
    1.35
    Bal
    1.27
     BAL
    1.05
    bal
    1.04
     бал
    1.01
    bala
    0.96
    BAL
    0.92
    zembro
    0.87
    balan
    0.85
    Activations Density 0.023%

    No Known Activations