© 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. 22-GEMMASCOPE-RES-131K
    7. 128830
    Prev
    Next
    INDEX
    Explanations

    Q:Widthorbits Jupitercw

    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_22/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
    Echo
    -0.96
    wales
    -0.91
    WARE
    -0.88
    ToolStrip
    -0.88
    せば
    -0.87
    मे
    -0.86
    hemp
    -0.86
    ⃣
    -0.86
     absoluta
    -0.85
    ěst
    -0.85
    POSITIVE LOGITS
    お互
    1.00
    彼らの
    0.93
     leur
    0.87
     อา
    0.87
    どうやら
    0.86
    chitz
    0.82
    もしか
    0.82
     kr
    0.81
     oks
    0.81
     grin
    0.80
    Activations Density 0.000%

    No Known Activations