© 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. 10-GEMMASCOPE-RES-131K
    7. 74443
    Prev
    Next
    INDEX
    Explanations

    Stewart-Warner Corporation, Mann directed

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

    The neuron responds to long, multi-syllabic chemical or drug names—especially fragments of antidepressants (e.g. “ami-trip-tyline,” “paro-xetine,” etc.).

    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
    <td>
    -1.58
    anız
    -1.57
     his
    -1.55
    %
    -1.48
     anyone
    -1.47
     its
    -1.45
    &
    -1.43
     anybody
    -1.42
     current
    -1.41
     کم
    -1.40
    POSITIVE LOGITS
    鱟
    1.59
     confirmación
    1.51
     OPPORTUNITY
    1.45
    這些
    1.44
    </h5>
    1.40
    必要があります
    1.39
    zzlement
    1.38
    рії
    1.36
    </h3>
    1.35
     these
    1.34
    Activations Density 4.984%

    No Known Activations