© 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. 10-GEMMASCOPE-RES-131K
    7. 15126
    Prev
    Next
    INDEX
    Explanations

    UIImageView or ImageView

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on mentions of ImageView (e.g. the XML tag or class name), i.e. it detects references to ImageView in code or layouts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    D
    -3.17
    }$
    -2.89
    M
    -2.55
    2
    -2.52
     infused
    -2.50
    A
    -2.45
    تیجه
    -2.41
    哪怕
    -2.34
    }
    -2.33
    },
    -2.33
    POSITIVE LOGITS
    してみると
    2.84
    迨
    2.64
     verſ
    2.61
    隳
    2.59
    灕
    2.55
     ſy
    2.48
     rapports
    2.42
    鹟
    2.39
    ︕
    2.38
    しなければ
    2.33
    Activations Density 0.001%

    No Known Activations