© 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. 66154
    Prev
    Next
    INDEX
    Explanations

    opportunity to win, buy, teach

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

    The neuron fires strongly on “to” when it introduces promotional or call-to-action infinitives (e.g. “opportunity to win/buy/teach/develop”).

    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
    蚍
    -1.22
     there
    -1.22
     memastikan
    -1.14
     they
    -1.13
     proveedores
    -1.12
     enabling
    -1.12
     contenidos
    -1.11
     entail
    -1.11
    foundland
    -1.10
     bellissima
    -1.10
    POSITIVE LOGITS
     opportunity
    1.56
     зустрі
    1.47
     більш
    1.27
     можли
    1.26
    쨰
    1.25
     OPPORTUNITY
    1.24
     debatable
    1.23
     moletom
    1.20
     возможность
    1.18
     який
    1.17
    Activations Density 0.014%

    No Known Activations