© 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. 1200
    Prev
    Next
    INDEX
    Explanations

    side, Q, mini

    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
     subdivisions
    -0.82
     Occasional
    -0.80
     вік
    -0.79
    ธ์
    -0.77
     Behold
    -0.77
     occasional
    -0.77
     sztuki
    -0.75
     Ibid
    -0.75
     helpline
    -0.75
    hahaha
    -0.73
    POSITIVE LOGITS
    Side
    0.84
     Side
    0.83
     ques
    0.79
     فى
    0.77
     Eggers
    0.76
     STORIES
    0.74
    Спо
    0.74
     трубо
    0.74
     你
    0.74
     сторону
    0.73
    Activations Density 0.029%

    No Known Activations