© 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. 64086
    Prev
    Next
    INDEX
    Explanations

    licensing and documentation comments

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

    The neuron detects occurrences of the “Remarks” section heading (i.e. the word “Remarks” marking a documentation or comment block).

    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
    Успе
    -0.78
     rolex
    -0.76
    гота
    -0.76
     loob
    -0.76
    🍰
    -0.76
     Lockdown
    -0.74
     VOUS
    -0.74
     Grille
    -0.73
     Eurosport
    -0.73
     ¥
    -0.73
    POSITIVE LOGITS
    mz
    0.81
     liaison
    0.80
    凝
    0.77
     composure
    0.77
     accusations
    0.72
     pelvis
    0.71
     oamen
    0.70
    aguay
    0.70
     deportivos
    0.70
     кі
    0.69
    Activations Density 0.001%

    No Known Activations