© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73491
    Prev
    Next
    INDEX
    Explanations

    apache license url

    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
    オススメ
    -0.77
    参数
    -0.72
    Julius
    -0.70
    كرة
    -0.69
    webf
    -0.68
    abia
    -0.67
    рас
    -0.66
    ャ
    -0.66
     argv
    -0.66
    да
    -0.65
    POSITIVE LOGITS
    eat
    0.66
     negoci
    0.65
     otor
    0.65
    otal
    0.64
     boite
    0.64
    distant
    0.61
    setCancelable
    0.61
    inkled
    0.60
     warrants
    0.60
    gradients
    0.59
    Activations Density 0.112%

    No Known Activations