© 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. 22-GEMMASCOPE-RES-131K
    7. 34450
    Prev
    Next
    INDEX
    Explanations

    no such thing as

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

    The neuron detects occurrences of the idiomatic phrase “no such thing as.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    蟶
    -1.14
     TreeNode
    -1.09
     TAMBÉM
    -1.03
     trám
    -1.02
     spesso
    -1.00
     قصد
    -1.00
     ope
    -0.99
     doubtnut
    -0.99
     kapture
    -0.98
    有些
    -0.98
    POSITIVE LOGITS
     any
    1.81
     good
    1.22
     in
    1.22
    !!!!
    1.21
     this
    1.20
     as
    1.20
     only
    1.16
    !!!!!
    1.13
     really
    1.10
     can
    1.09
    Activations Density 0.026%

    No Known Activations