© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66477
    Prev
    Next
    INDEX
    Explanations

    (parentheses with content)

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

    The neuron identifies mentions of a topical medication (e.g. a “-ramine” cream) and its application dosage.

    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
     participer
    -1.13
    ELTS
    -1.09
     ΤΟ
    -1.09
    ांकि
    -1.08
    vonne
    -1.06
    zzet
    -1.04
     CONCLUS
    -1.02
     Redacción
    -1.02
    сько
    -1.01
     السف
    -1.01
    POSITIVE LOGITS
     also
    1.38
     with
    1.24
     тоже
    1.16
     should
    1.10
     its
    1.09
     which
    1.02
     high
    0.96
     around
    0.96
     without
    0.95
     just
    0.94
    Activations Density 0.058%

    No Known Activations