© 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. 34-GEMMASCOPE-RES-131K
    7. 107967
    Prev
    Next
    INDEX
    Explanations

    online event information

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

    The neuron strongly activates on multiword title‐case phrases—especially event names, headings, or branded proper‐noun sequences.

    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
     защото
    -0.82
    namn
    -0.81
    NPR
    -0.81
    estos
    -0.80
    naam
    -0.79
    செ
    -0.79
     Molo
    -0.78
     Моло
    -0.76
    ША
    -0.76
    อน
    -0.75
    POSITIVE LOGITS
     fans
    1.34
     fan
    1.34
     Fan
    1.19
     Fans
    1.16
    fan
    1.12
     ticket
    1.05
     activation
    1.02
     player
    0.95
     interactive
    0.95
    Fans
    0.91
    Activations Density 0.066%

    No Known Activations