© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56958
    Prev
    Next
    INDEX
    Explanations

    post-traumatic stress disorder

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

    legal terms, licenses, and document formatting elements.

    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_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
     Verantwortung
    -0.73
     Cutting
    -0.71
    Here
    -0.64
    hawat
    -0.64
     Cuts
    -0.63
    Cutting
    -0.63
    While
    -0.62
     Insertion
    -0.62
    ղ
    -0.60
     forward
    -0.60
    POSITIVE LOGITS
     gelegen
    0.72
    Impulse
    0.69
    чак
    0.68
    Demografia
    0.68
    chting
    0.67
    intre
    0.66
     mujer
    0.66
    CADE
    0.66
    IMP
    0.66
     Biblia
    0.66
    Activations Density 0.072%

    No Known Activations