© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43222
    Prev
    Next
    INDEX
    Explanations

    campaigns and related actions

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

    The neuron detects occurrences of the word “campaign” (including its plural form).

    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
    ).
    -2.06
    我先
    -1.88
    "
    -1.80
     showcased
    -1.76
     who
    -1.75
    同上
    -1.67
     there
    -1.66
    乄
    -1.66
     seeing
    -1.64
     голубой
    -1.64
    POSITIVE LOGITS
     المثال
    2.17
     –
    1.93
     vorigen
    1.92
     to
    1.81
    簓
    1.80
    ſtra
    1.77
    诽
    1.74
     billboard
    1.73
    诋
    1.73
    洇
    1.71
    Activations Density 0.022%

    No Known Activations