© 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. 123607
    Prev
    Next
    INDEX
    Explanations

    recording followed by context

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

    The neuron flags any mention of “record” in its various forms—e.g. words about recording or recorded media.

    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
    s
    -4.38
    2
    -4.16
    \
    -3.69
    4
    -3.64
    7
    -3.30
    1
    -3.25
    6
    -3.14
    3
    -3.05
    8
    -2.97
    5
    -2.80
    POSITIVE LOGITS
    灕
    3.22
    欵
    3.09
    甡
    3.06
    嚶
    3.05
    難易
    3.02
    玙
    2.91
    怎么说
    2.83
    icksburg
    2.78
    癩
    2.78
    汭
    2.75
    Activations Density 0.017%

    No Known Activations