© 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. 14134
    Prev
    Next
    INDEX
    Explanations

    looked at

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

    The neuron detects instances of “look” (e.g. look, looked) in the text.

    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
     huom
    -1.67
     when
    -1.64
     biografi
    -1.63
     africano
    -1.57
     australiano
    -1.55
     divino
    -1.52
     multiuso
    -1.51
     asli
    -1.49
     three
    -1.48
     both
    -1.45
    POSITIVE LOGITS
     into
    1.60
    </strong>
    1.46
    なども
    1.36
     dejando
    1.34
    などは
    1.29
     instill
    1.27
     Políticas
    1.26
     psicología
    1.26
    玥
    1.24
    がありました
    1.23
    Activations Density 0.044%

    No Known Activations