© 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. 77265
    Prev
    Next
    INDEX
    Explanations

    dust settling or collecting

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

    The neuron activates on mentions of unwanted small solid particulates (dust, dirt, debris, trash).

    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
    燮
    -0.94
    داران
    -0.90
    手を
    -0.87
     注
    -0.83
     effluents
    -0.82
     Emergence
    -0.80
    覗
    -0.80
     líquido
    -0.79
    gemeente
    -0.78
    fram
    -0.77
    POSITIVE LOGITS
     deposited
    1.64
     deposit
    1.29
    settled
    1.17
     settles
    1.16
     settle
    1.13
     adhering
    1.13
     settled
    1.13
     collected
    1.11
     clinging
    1.08
     lodged
    1.07
    Activations Density 0.072%

    No Known Activations