© 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. 34-GEMMASCOPE-RES-131K
    7. 63331
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    マイナス
    -0.74
    épreuve
    -0.70
     mdf
    -0.68
     करके
    -0.67
    拍攝
    -0.66
    dema
    -0.65
     sergio
    -0.65
    风的
    -0.64
     clínicas
    -0.64
     moeili
    -0.64
    POSITIVE LOGITS
     P
    1.36
     R
    1.02
     S
    0.98
     Q
    0.97
     T
    0.84
     L
    0.79
     RQ
    0.78
     Article
    0.77
     M
    0.77
     Minute
    0.76
    Activations Density 0.218%

    No Known Activations