© 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. 10-GEMMASCOPE-RES-131K
    7. 99886
    Prev
    Next
    INDEX
    Explanations

    has nothing to do with

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

    This neuron specializes in detecting phrases that state irrelevance, such as “has nothing to do with” (and related “something to do with”) constructions.

    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
    𓋼
    -2.20
     a
    -1.91
     when
    -1.91
     in
    -1.77
    इटम
    -1.73
    energies
    -1.67
     with
    -1.66
    ቍ
    -1.64
    ി
    -1.63
    琹
    -1.61
    POSITIVE LOGITS
     möglichen
    1.61
     работают
    1.60
     มี
    1.58
    どういう
    1.54
     celebrates
    1.53
    对自己
    1.49
    見えます
    1.45
    カッコいい
    1.45
     Herbs
    1.45
     เป็น
    1.44
    Activations Density 0.017%

    No Known Activations