© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92682
    Prev
    Next
    INDEX
    Explanations

    recording and reproducing information

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

    The neuron strongly activates on patent-style technical terms around recording media and apparatus (e.g. “recording,” “record,” “media,” “optical disc”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    *{-
    -0.73
    hringer
    -0.69
    setKey
    -0.69
    eles
    -0.68
    Ofic
    -0.67
    wei
    -0.66
     Norwalk
    -0.66
     旅
    -0.65
     contral
    -0.65
    explained
    -0.64
    POSITIVE LOGITS
     tracks
    1.09
     track
    1.05
     TRACK
    1.03
     Tracks
    0.97
    Track
    0.96
     Track
    0.93
    TRACK
    0.88
    TOC
    0.86
     TOC
    0.85
    Session
    0.84
    Activations Density 0.058%

    No Known Activations