© 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. 22-GEMMASCOPE-RES-131K
    7. 65414
    Prev
    Next
    INDEX
    Explanations

    health and disability challenges

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

    descriptions of people with disabilities, illnesses, or special needs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    nibal
    -1.20
     inexist
    -1.13
    煨
    -1.12
     sangu
    -1.10
    tront
    -1.09
    コスパ
    -1.09
     canin
    -1.09
     sauf
    -1.08
     effici
    -1.08
     commerces
    -1.07
    POSITIVE LOGITS
     or
    2.20
    又は
    1.45
    または
    1.30
    или
    1.23
     Chúng
    1.21
     needs
    1.19
     ngào
    1.18
     ideen
    1.17
     либо
    1.16
    Externé
    1.16
    Activations Density 0.068%

    No Known Activations