© 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. 31579
    Prev
    Next
    INDEX
    Explanations

    CUDA drivers and GTX

    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
    CPU
    -0.93
     CPU
    -0.93
    cpu
    -0.90
     ТВ
    -0.87
    **************
    -0.85
    rina
    -0.80
     cpu
    -0.80
    Ꭲ
    -0.79
     CRO
    -0.79
    ("/
    -0.78
    POSITIVE LOGITS
     proprietors
    0.90
     insufficiency
    0.82
    Testo
    0.77
     設置
    0.76
     enabled
    0.75
     Toolkit
    0.74
    bomba
    0.73
     встанов
    0.73
     nastav
    0.72
    痕迹
    0.71
    Activations Density 0.018%

    No Known Activations