© 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. 34-GEMMASCOPE-RES-131K
    7. 106541
    Prev
    Next
    INDEX
    Explanations

    determination of mental illness descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     loan
    -0.91
    řev
    -0.91
     borrow
    -0.90
    obraz
    -0.83
     perhaps
    -0.83
     large
    -0.82
     membuk
    -0.79
     highly
    -0.79
    Elliot
    -0.77
     loans
    -0.77
    POSITIVE LOGITS
     サイド
    0.86
     calme
    0.84
    boo
    0.84
    ienka
    0.83
    pay
    0.82
    aryen
    0.82
    POINTS
    0.81
    tra
    0.81
    bulb
    0.81
    രിക്ക
    0.80
    Activations Density 0.015%

    No Known Activations