© 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. 64090
    Prev
    Next
    INDEX
    Explanations

    media and press releases

    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
     immobilized
    -0.79
     повідом
    -0.72
    GRUPO
    -0.71
    sponsored
    -0.71
    ‌ای
    -0.69
    🧴
    -0.67
    헙
    -0.67
    ialog
    -0.67
    ዊ
    -0.67
     anticor
    -0.66
    POSITIVE LOGITS
     media
    1.73
     journalists
    1.56
    media
    1.43
     журнали
    1.34
     Media
    1.34
    Media
    1.33
    媒体
    1.28
     press
    1.26
    MEDIA
    1.25
     MEDIA
    1.24
    Activations Density 0.019%

    No Known Activations