© 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. 47772
    Prev
    Next
    INDEX
    Explanations

    names starting with G or J

    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
    opheles
    -0.78
    baş
    -0.78
     الصين
    -0.77
    맏
    -0.77
    tiche
    -0.75
     cómics
    -0.74
     financière
    -0.73
     ภาพ
    -0.73
    决赛
    -0.73
     DOLLARS
    -0.72
    POSITIVE LOGITS
     가
    0.94
    班
    0.90
     render
    0.81
    湿度
    0.80
    思索
    0.78
    ânsito
    0.76
     embellished
    0.76
     λ
    0.75
    POSSIBLE
    0.75
     加
    0.73
    Activations Density 0.009%

    No Known Activations