© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38607
    Prev
    Next
    INDEX
    Explanations

    PWID, NEET youths, nulliparous, primiparous, UE

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

    specialized population identifiers in medical and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates strongly on specialized medical study population descriptors (e.g. “inject,” “drugs,” “PWID,” “nulliparous,” “multiparous”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     and
    -1.07
     Jornal
    -0.98
     populer
    -0.97
     perfekt
    -0.96
     to
    -0.96
    ButtonModule
    -0.93
     „
    -0.91
     sportivo
    -0.91
     paiement
    -0.91
     pez
    -0.91
    POSITIVE LOGITS
     who
    1.26
     ciudadano
    1.13
    empêcher
    1.10
     hroz
    1.09
     található
    1.07
     gänzlich
    1.06
    під
    1.05
     cementerio
    1.05
     происходит
    1.04
     traités
    1.04
    Activations Density 0.215%

    No Known Activations