© 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. 10-GEMMASCOPE-RES-131K
    7. 85104
    Prev
    Next
    INDEX
    Explanations

    medical or Android development topics

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

    The neuron activates almost exclusively on occurrences of the Android ArrayAdapter class (and its creation methods).

    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
    咘
    -2.27
    '
    -2.27
    ﹔
    -2.22
    O
    -2.19
    ſſen
    -2.19
    </h3>
    -2.14
    佧
    -2.08
    쥘
    -2.03
     zugel
    -2.02
    "),
    -2.00
    POSITIVE LOGITS
    }
    2.56
    as
    2.09
     Notably
    1.85
    ஂ
    1.85
    and
    1.84
     впечатление
    1.84
    one
    1.82
     deter
    1.82
    一说
    1.78
     unpredictable
    1.76
    Activations Density 0.000%

    No Known Activations