© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30631
    Prev
    Next
    INDEX
    Explanations

    /* and // comments

    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
     infeliz
    -0.97
    ář
    -0.91
     Geste
    -0.85
    therape
    -0.83
     pedas
    -0.83
    ONIC
    -0.81
     Mön
    -0.80
    intval
    -0.80
     Menge
    -0.79
    rechte
    -0.78
    POSITIVE LOGITS
     være
    0.85
     puissante
    0.80
    WAYS
    0.76
    ϯ
    0.75
     sprawdz
    0.75
    eneuve
    0.75
    lifford
    0.74
    设置为
    0.74
    你了
    0.72
     ngừng
    0.72
    Activations Density 0.014%

    No Known Activations