© 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. 35536
    Prev
    Next
    INDEX
    Explanations

    emotional development

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

    This neuron is highly sensitive to capitalized terms and proper names (i.e. named entities or title-case words).

    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
    seit
    -1.18
    سوال
    -1.13
    Özel
    -1.09
    гән
    -1.09
    栳
    -1.05
     keer
    -1.05
    titure
    -1.04
    legt
    -1.04
     sécur
    -1.03
    AddHtmlAttribute
    -1.02
    POSITIVE LOGITS
     this
    1.13
     here
    1.10
     in
    1.08
     faster
    1.06
     jogja
    1.04
     when
    1.00
     gradually
    0.98
    valentino
    0.97
     at
    0.96
     local
    0.95
    Activations Density 0.030%

    No Known Activations