© 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. 2549
    Prev
    Next
    INDEX
    Explanations

    variables like X, x, XY, n, str

    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
    셨
    -0.86
    ustus
    -0.82
    nologi
    -0.81
    Ikke
    -0.79
     IPs
    -0.79
    ６
    -0.75
    "}}>
    -0.75
    жик
    -0.75
     Tencent
    -0.75
     [&
    -0.75
    POSITIVE LOGITS
     x
    3.48
     X
    3.09
    X
    2.36
    x
    2.27
     XYZ
    1.69
     xyz
    1.63
    getX
    1.57
    GetX
    1.45
    𝑥
    1.36
    xyz
    1.31
    Activations Density 0.151%

    No Known Activations