© 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. 70987
    Prev
    Next
    INDEX
    Explanations

    find it

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

    The neuron selectively activates on the verb “find” (especially in constructions like “find it …” or “we find …”).

    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
     a
    -2.25
     both
    -1.68
     know
    -1.67
     lutego
    -1.64
     three
    -1.56
    l
    -1.55
    坩
    -1.50
     one
    -1.48
     two
    -1.48
     Wirken
    -1.46
    POSITIVE LOGITS
     that
    2.20
    鹮
    1.97
    还不错
    1.80
    ⧠
    1.76
     befes
    1.70
    橚
    1.65
     gewor
    1.59
     chances
    1.59
    还是很
    1.58
     angebracht
    1.55
    Activations Density 0.027%

    No Known Activations