© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94019
    Prev
    Next
    INDEX
    Explanations

    copyright reserved

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags boilerplate license and copyright/legal terms (e.g. “Apple,” “Inc,” “rights,” “distribution,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    DataPropertyName
    -0.81
     حركة
    -0.79
    äische
    -0.79
    Compressor
    -0.77
     raport
    -0.77
     acier
    -0.77
     lika
    -0.77
     deterred
    -0.77
     Speisen
    -0.76
     doar
    -0.76
    POSITIVE LOGITS
     engagements
    0.76
    iraj
    0.73
    etero
    0.70
    先代
    0.70
    iburg
    0.69
    既に
    0.69
    不让
    0.68
     khususnya
    0.68
    walde
    0.67
    mahan
    0.66
    Activations Density 0.013%

    No Known Activations