© 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. 10-GEMMASCOPE-RES-131K
    7. 73717
    Prev
    Next
    INDEX
    Explanations

    efectos secundarios

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

    This neuron activates for pharmaceutical drug names and medication-related information.

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

    The neuron flags mentions of pharmaceutical products together with their dosage specifications (e.g. drug names plus milligram amounts or parenthesized active ingredients).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    siehe
    -1.29
     potret
    -1.18
    dijual
    -1.17
    \%,
    -1.17
     bestia
    -1.16
    قليم
    -1.16
     djur
    -1.15
    ḏ
    -1.13
    …»
    -1.13
     okam
    -1.12
    POSITIVE LOGITS
     we
    1.41
     there
    1.32
    self
    1.23
     now
    1.22
    rapeau
    1.21
    不是很
    1.20
    ּוֹ
    1.19
     time
    1.17
    slot
    1.15
    withOpacity
    1.15
    Activations Density 0.015%

    No Known Activations