© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22854
    Prev
    Next
    INDEX
    Explanations

    interference concepts

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

    The neuron fires on occurrences of the root “interfer” (e.g. words like “interfere” or “interference”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    𐐪
    -2.81
    If
    -2.80
    As
    -2.78
    With
    -2.61
     WITH
    -2.58
    When
    -2.53
    with
    -2.47
    N
    -2.41
    钞
    -2.39
     versatile
    -2.38
    POSITIVE LOGITS
    }
    3.42
    趼
    3.11
    皝
    2.94
    猹
    2.53
    ,"
    2.50
     แปล
    2.42
    蜮
    2.41
    
    2.34
    
    2.34
    </h3>
    2.31
    Activations Density 0.011%

    No Known Activations