© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66023
    Prev
    Next
    INDEX
    Explanations

    accessible and affordable

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

    The neuron fires on promotional/business-jargon phrases—especially corporate mission–style statements built around “is to …,” “with …,” and similar goal-oriented infinitives.

    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
    scaron
    -0.77
    ându
    -0.77
    uté
    -0.77
    rogation
    -0.73
     günü
    -0.73
    unique
    -0.73
    vedi
    -0.72
    Enllaces
    -0.72
    ماء
    -0.70
    媽媽
    -0.70
    POSITIVE LOGITS
     accessible
    4.16
     accessibility
    4.06
    accessible
    3.50
     доступ
    3.30
     Accessible
    3.27
     democrati
    3.19
    Accessible
    3.14
     Accessibility
    3.13
    accessibility
    3.11
    Accessibility
    2.97
    Activations Density 0.073%

    No Known Activations