© 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. 34-GEMMASCOPE-RES-131K
    7. 79086
    Prev
    Next
    INDEX
    Explanations

    election polls

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

    The neuron strongly activates on quantitative and statistical terms—numbers, percentages, poll figures, and other numeric data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ⊖
    -0.76
    पन
    -0.76
     señores
    -0.75
    挝
    -0.74
     bridesmaids
    -0.69
    ('@
    -0.68
     bitumen
    -0.68
     Plen
    -0.68
     Fußballspieler
    -0.68
    EdgeInsets
    -0.67
    POSITIVE LOGITS
     polls
    6.16
     poll
    5.69
    poll
    4.59
     polling
    4.41
    polls
    4.25
    Poll
    4.25
     Polls
    4.19
     Poll
    4.13
     POLL
    4.03
    POLL
    3.70
    Activations Density 0.090%

    No Known Activations