© 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. 32277
    Prev
    Next
    INDEX
    Explanations

    development and global issues

    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
     ДЛЯ
    -1.05
    谈判
    -1.04
    遠く
    -0.93
     ВЫ
    -0.93
    There
    -0.92
    ごちそうさまでした
    -0.90
     razões
    -0.89
    Tore
    -0.88
    ratore
    -0.88
    ೮
    -0.87
    POSITIVE LOGITS
     education
    1.91
     health
    1.76
     climate
    1.49
     Education
    1.47
     environment
    1.45
     agriculture
    1.43
     energy
    1.39
     Health
    1.29
    education
    1.22
     security
    1.16
    Activations Density 0.032%

    No Known Activations