© 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. 104404
    Prev
    Next
    INDEX
    Explanations

    iPhone model numbers

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

    iPhone model numbers and versions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron specifically detects standalone numeric tokens (digits or numbers) in the text.

    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
    .”
    -1.67
     a
    -1.64
     sufficient
    -1.63
     Werden
    -1.50
    就算是
    -1.48
    翱
    -1.47
    擒
    -1.45
    8
    -1.44
    糅
    -1.41
     cualquier
    -1.40
    POSITIVE LOGITS
     всем
    1.70
     всех
    1.52
     จาก
    1.46
     preservar
    1.44
    uminum
    1.41
    套装
    1.38
    غيرة
    1.37
     colorear
    1.37
    买的
    1.36
     transformar
    1.35
    Activations Density 0.008%

    No Known Activations