© 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. 1017
    Prev
    Next
    INDEX
    Explanations

    Cupertino, Apple, iOS, Xcode

    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
    onesa
    -0.82
    imura
    -0.81
     whatsoever
    -0.81
    くなった
    -0.74
    ベート
    -0.73
    ô
    -0.71
    dende
    -0.71
    
    -0.70
     Dubuque
    -0.69
    пня
    -0.69
    POSITIVE LOGITS
     Cupertino
    1.36
     Apple
    1.32
    Apple
    1.13
     Xcode
    1.07
     iOS
    1.06
    Cu
    0.99
     ябло
    0.98
    iOS
    0.92
    apple
    0.91
     Cu
    0.91
    Activations Density 0.000%

    No Known Activations