© 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. 60100
    Prev
    Next
    INDEX
    Explanations

    perspective and points of view

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

    The neuron flags high‐register, academic‐style language—words common in formal research or study contexts (e.g. from, perspective, international, student, cost-effectiveness).

    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
    aglia
    -0.77
    сели
    -0.77
    ="#
    -0.76
     Đà
    -0.75
    ánló
    -0.75
    Recommendations
    -0.75
    тип
    -0.75
     精
    -0.74
    endregion
    -0.74
    pling
    -0.73
    POSITIVE LOGITS
     perspective
    6.75
     perspectives
    5.16
    perspective
    5.00
     Perspective
    4.75
    Perspective
    4.63
     viewpoint
    4.34
     perspectiva
    4.06
     PERSPECT
    3.81
     perspek
    3.66
     Perspectives
    3.58
    Activations Density 0.082%

    No Known Activations