© 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. 117785
    Prev
    Next
    INDEX
    Explanations

    Apple and its 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
    ]")]
    -0.78
     irresponsible
    -0.74
    絆
    -0.69
    vk
    -0.68
     motor
    -0.68
    }")]
    -0.66
    に行ってきました
    -0.66
     Leonard
    -0.66
     cosplay
    -0.66
    伝統
    -0.65
    POSITIVE LOGITS
    Apple
    1.64
     Apple
    1.63
     APPLE
    1.18
     Cupertino
    1.18
    APPLE
    1.14
     iCloud
    1.11
    apple
    1.09
     apple
    0.99
     ябло
    0.97
     Apples
    0.96
    Activations Density 0.021%

    No Known Activations