© 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. 48087
    Prev
    Next
    INDEX
    Explanations

    tablet computers

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

    The neuron is triggered by mentions of “tablet” (often in the phrase “tablet computer” or related tablet-device terminology).

    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
    的那
    -3.02
    的就
    -2.56
    졍
    -2.55
    綃
    -2.55
    之时
    -2.55
    書いた
    -2.47
    𝝈
    -2.33
    的東西
    -2.30
    皝
    -2.27
     unn
    -2.22
    POSITIVE LOGITS
    <bos>
    3.31
    𓋼
    3.23
    衕
    2.92
     establish
    2.69
    Are
    2.64
    Here
    2.64
    because
    2.61
    Making
    2.53
    Ｇ
    2.53
     häufigsten
    2.52
    Activations Density 0.005%

    No Known Activations