© 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. 34-GEMMASCOPE-RES-131K
    7. 65237
    Prev
    Next
    INDEX
    Explanations

    fascinated, fascicle, fascism, fascial

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

    The neuron responds to the letter sequence “fas” (e.g. in “Fas,” “fascic,” “FAS,” 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_34/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
     paga
    -0.88
    ribut
    -0.85
     cocok
    -0.84
     Agustín
    -0.83
    ⃟
    -0.82
     geschieht
    -0.82
     Acht
    -0.81
     vulnerables
    -0.81
     naturel
    -0.79
     leal
    -0.79
    POSITIVE LOGITS
     Fas
    1.57
    Fas
    1.55
     fas
    1.18
    fas
    1.12
     Fass
    1.04
     FAS
    1.02
     fascin
    1.00
     fascism
    0.96
     fascic
    0.95
     fascia
    0.90
    Activations Density 0.021%

    No Known Activations