© 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. 63648
    Prev
    Next
    INDEX
    Explanations

    abortion and pregnancy loss

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

    medical and research text discussing pregnancy loss, stillbirths, and abortions.

    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
     assemble
    -0.74
    累计
    -0.71
     paro
    -0.71
     sum
    -0.70
    war
    -0.70
    が入
    -0.70
    lo
    -0.70
    unes
    -0.69
     afec
    -0.69
     daw
    -0.69
    POSITIVE LOGITS
     miscarriage
    2.56
     mis
    1.57
     losses
    1.56
     loss
    1.54
    losses
    1.30
     Losses
    1.26
    Mis
    1.20
    Loss
    1.19
     Loss
    1.15
     loses
    1.13
    Activations Density 0.037%

    No Known Activations