© 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. 72807
    Prev
    Next
    INDEX
    Explanations

    stakeholders

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

    The neuron detects occurrences of the word “stakeholder” (and its plural “stakeholders”).

    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
    ’
    -3.13
     The
    -2.81
     This
    -2.67
     With
    -2.52
    出て
    -2.22
    </i>
    -2.14
     we
    -2.11
     Then
    -2.05
     konusunda
    -2.05
     It
    -1.99
    POSITIVE LOGITS
     pérd
    2.88
    titial
    2.58
    𞤪
    2.56
     elek
    2.47
    ܞ
    2.41
    ೢ
    2.38
    豨
    2.36
    ༵
    2.36
     zina
    2.34
     papir
    2.28
    Activations Density 0.003%

    No Known Activations