© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59195
    Prev
    Next
    INDEX
    Explanations

    depression and suppression

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

    The neuron selectively responds to words related to pressure or tension (e.g. containing roots like “press/pression” or “tensive”).

    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
    玫
    -0.96
    iju
    -0.88
     incorporate
    -0.86
    дава
    -0.84
     processes
    -0.84
     '
    -0.82
     a
    -0.82
     procedures
    -0.80
     process
    -0.80
     in
    -0.78
    POSITIVE LOGITS
    
    1.07
    ileo
    1.01
    depress
    0.97
     húmedo
    0.97
     Baller
    0.97
     Abingdon
    0.94
     peuples
    0.93
     Herpes
    0.92
    Че
    0.91
     mögliche
    0.91
    Activations Density 0.055%

    No Known Activations