© 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. 117085
    Prev
    Next
    INDEX
    Explanations

    HTML tags like `</title>`, `<code>`, or closing angle brackets

    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
    litos
    -0.78
    던
    -0.71
    dited
    -0.71
     if
    -0.70
     dần
    -0.69
    plr
    -0.69
    …~
    -0.69
     Purposes
    -0.68
     resolved
    -0.68
     Lijst
    -0.68
    POSITIVE LOGITS
    Could
    1.03
     Could
    0.91
    TintMode
    0.75
     Accountant
    0.75
    ATTACH
    0.73
     Cuen
    0.72
    Incorrect
    0.71
     candies
    0.71
     πως
    0.70
    Kami
    0.69
    Activations Density 0.017%

    No Known Activations