© 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. 65087
    Prev
    Next
    INDEX
    Explanations

    ura suffix

    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
     Ві
    -0.75
    traversal
    -0.75
     VISA
    -0.73
    UiThread
    -0.73
    ウィキ
    -0.72
    éton
    -0.71
     Во
    -0.69
     чого
    -0.69
    гите
    -0.68
     nhắc
    -0.68
    POSITIVE LOGITS
    ätigkeit
    0.79
    onsense
    0.74
    塗
    0.73
    ꈍ
    0.72
    march
    0.71
     sindical
    0.70
    irm
    0.70
    Bootstrap
    0.69
     baixar
    0.69
     americano
    0.69
    Activations Density 0.028%

    No Known Activations