© 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. 93419
    Prev
    Next
    INDEX
    Explanations

    same or similar

    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
    ==-
    -0.87
     nigdy
    -0.84
     mContext
    -0.81
    tius
    -0.81
     deleteAll
    -0.78
    зина
    -0.77
    ">\
    -0.76
    忿
    -0.76
    urilor
    -0.76
     deportivas
    -0.76
    POSITIVE LOGITS
     almost
    3.95
    ほぼ
    3.67
     почти
    3.50
     basically
    3.45
     تقری
    3.38
    almost
    3.36
     essentially
    3.36
     virtually
    3.31
     практически
    3.31
     nearly
    3.28
    Activations Density 0.200%

    No Known Activations