© 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. 77847
    Prev
    Next
    INDEX
    Explanations

    making recommendations

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

    The neuron detects formal report‐style or policy‐document wording—i.e. the kind of high‐register, authoritative prose (titles, headings, “provides,” “recommendation,” “sets out,” etc.) found in official reports.

    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
     eſt
    -0.93
     garan
    -0.88
    voer
    -0.86
     LCCN
    -0.82
     ledig
    -0.81
    ैल
    -0.81
    мышлен
    -0.77
    fäl
    -0.77
     concours
    -0.77
    urgia
    -0.75
    POSITIVE LOGITS
     recommendations
    6.47
     recommendation
    5.53
     Recommendations
    4.72
     recommended
    4.66
    Recommendations
    4.63
     recommend
    4.53
    recommendations
    4.41
     recommends
    4.03
     recommending
    3.94
    Recommendation
    3.83
    Activations Density 0.051%

    No Known Activations