© 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. 9357
    Prev
    Next
    INDEX
    Explanations

    iPad and its models

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

    The neuron activates on mentions of Apple’s iOS hardware—especially the iPad (and its variants) and related devices like the iPhone/iPod.

    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
    ⛦
    -2.75
     —
    -2.63
    ↵
    -2.52
    愎
    -2.44
     inconce
    -2.36
    崛
    -2.34
    ⭏
    -2.31
    ’
    -2.28
    selbe
    -2.20
    
    -2.20
    POSITIVE LOGITS
    ]
    2.48
    c
    2.36
     The
    2.06
    derdag
    2.06
    '),
    2.05
    I
    2.03
    ',
    2.00
    "},
    1.98
    },
    1.95
    鱟
    1.93
    Activations Density 0.008%

    No Known Activations