© 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. 10-GEMMASCOPE-RES-131K
    7. 71028
    Prev
    Next
    INDEX
    Explanations

    notes email

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

    The neuron activates on occurrences of the word “Notes” used as a section heading or label.

    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
    ⡪
    -3.16
    0
    -2.67
    肏
    -2.53
    媪
    -2.39
     peluche
    -2.34
    粜
    -2.33
    背影
    -2.33
    
    -2.30
    ఽ
    -2.23
    就已经
    -2.19
    POSITIVE LOGITS
     notes
    2.83
     perils
    2.55
    葙
    2.47
    Notes
    2.33
    实话
    2.31
     even
    2.22
     heath
    2.13
    緻
    2.13
     In
    2.09
     owing
    2.09
    Activations Density 0.004%

    No Known Activations