© 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. 31537
    Prev
    Next
    INDEX
    Explanations

    configuration keys

    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
    持ち
    -0.76
     doble
    -0.75
     धन
    -0.73
    рят
    -0.72
     convid
    -0.70
    navi
    -0.70
     arquitetura
    -0.69
     conj
    -0.69
     העולם
    -0.68
     anual
    -0.68
    POSITIVE LOGITS
    cli
    0.90
     Cli
    0.85
     EXCLUSIVE
    0.77
    页
    0.77
     Кли
    0.77
    去吧
    0.76
    õe
    0.75
    混合
    0.74
    poptotic
    0.74
     phải
    0.74
    Activations Density 0.015%

    No Known Activations