© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192623
    Prev
    Next
    INDEX
    Explanations

    therapy and rehabilitation services

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

    physical therapist rehabilitation

    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
    Negative Logits
    itore
    0.48
     Finanz
    0.47
    alloy
    0.44
    連結
    0.43
     nú
    0.41
     financiar
    0.41
    友情
    0.41
     perdagangan
    0.40
    毀
    0.39
    agem
    0.39
    POSITIVE LOGITS
     rehab
    0.80
     Rehab
    0.79
     rehabilit
    0.77
     therapists
    0.70
     rehabilitation
    0.68
     Rehabilitation
    0.65
     postural
    0.65
     rehabilitated
    0.65
     тера
    0.64
     rehabilitate
    0.64
    Activations Density 0.150%

    No Known Activations