© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83421
    Prev
    Next
    INDEX
    Explanations

    android UI, questions, technical terms

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

    This neuron activates on Java code instantiating or declaring an ArrayAdapter with its generic type parameters (e.g. new ArrayAdapter<...> or ArrayAdapter<CharSequence/String>).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     اللي
    -0.84
     ceva
    -0.82
     impelled
    -0.82
     strove
    -0.77
    Bibliograf
    -0.76
    țiunea
    -0.76
     น้ำ
    -0.75
    abetta
    -0.74
     slain
    -0.74
     invités
    -0.74
    POSITIVE LOGITS
    }.\
    0.80
    Objects
    0.77
    renders
    0.77
     objects
    0.76
    (‘
    0.75
    deno
    0.74
    绘
    0.74
     Walk
    0.74
     peringkat
    0.73
     notification
    0.73
    Activations Density 0.004%

    No Known Activations