© 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. 30353
    Prev
    Next
    INDEX
    Explanations

    iPhone and Apple products

    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
     Moray
    -0.85
    fæ
    -0.78
     lời
    -0.77
     HQ
    -0.74
    pc
    -0.74
    Ib
    -0.73
     utilizzato
    -0.72
     Spree
    -0.71
     Lovato
    -0.71
     Globo
    -0.71
    POSITIVE LOGITS
     iPhone
    1.49
     iPhones
    1.30
    iPhone
    1.18
     iphone
    1.16
     Pro
    0.99
     Apple
    0.92
    iphone
    0.88
     Iphone
    0.88
     Max
    0.85
    IPH
    0.82
    Activations Density 0.012%

    No Known Activations