© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 96136
    Prev
    Next
    INDEX
    Explanations

    PTSD trauma stress

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

    trauma and PTSD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    alámb
    0.41
     빠
    0.40
     अंश
    0.40
    recen
    0.39
     intercamb
    0.38
     finalidad
    0.38
    擀
    0.38
    ູ້
    0.38
     tangga
    0.38
     الانت
    0.38
    POSITIVE LOGITS
     traumat
    1.00
     trauma
    0.95
     Trauma
    0.90
     traum
    0.88
     traumatic
    0.81
     traumas
    0.80
     PTSD
    0.68
     survivor
    0.65
     survivors
    0.65
     трав
    0.63
    Activations Density 0.088%

    No Known Activations