© 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. 101110
    Prev
    Next
    INDEX
    Explanations

    Blender, Danielle, dashboard

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

    The neuron activates whenever the document mentions the software name “Blender.”

    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
     แต่
    -2.70
    瞜
    -2.59
     ſmall
    -2.56
    
    -2.50
    Адрес
    -2.50
    ㄛ
    -2.48
     ſever
    -2.48
    ญี่ป
    -2.44
     菇
    -2.44
     limpi
    -2.38
    POSITIVE LOGITS
    B
    3.77
    F
    3.36
    J
    3.27
    P
    3.27
    C
    3.22
    (
    3.20
    N
    3.20
    AL
    3.16
    L
    2.95
    H
    2.95
    Activations Density 0.005%

    No Known Activations