© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7809
    Prev
    Next
    INDEX
    Explanations

    memory, trauma, and healing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    டும்ப
    0.89
     பார்ப்ப
    0.87
     prakt
    0.85
    演
    0.85
    趣
    0.83
     испол
    0.81
    tyn
    0.81
     выступа
    0.80
     معلوم
    0.79
    꿔
    0.78
    POSITIVE LOGITS
     PTSD
    2.05
     trauma
    2.05
     reconstru
    2.02
    重建
    2.00
     aftermath
    1.98
     reintegr
    1.97
     Trauma
    1.92
     survivors
    1.92
     Recovery
    1.89
     recovering
    1.87
    Activations Density 0.609%

    No Known Activations