© 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. 34-GEMMASCOPE-RES-131K
    7. 99102
    Prev
    Next
    INDEX
    Explanations

    for a purpose or outcome

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

    The neuron recognizes formal purpose or mission clauses (e.g. “to … for the benefit of …”) in organizational or policy statements.

    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
     rhestr
    -0.79
     indivíduo
    -0.78
     enfoque
    -0.77
    SimpleDateFormat
    -0.75
    はこちらから
    -0.75
    Ꭱ
    -0.75
     Griffiths
    -0.74
     tradic
    -0.74
    Übernach
    -0.73
     Auffassung
    -0.72
    POSITIVE LOGITS
     benefit
    4.75
    benefit
    3.66
    Benefit
    3.48
     Benefit
    3.20
     benefits
    3.06
     beneficio
    3.00
     benefiting
    2.80
     benefited
    2.53
    Benefits
    2.33
     BENE
    2.33
    Activations Density 0.033%

    No Known Activations