© 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. 22-GEMMASCOPE-RES-131K
    7. 98322
    Prev
    Next
    INDEX
    Explanations

    outdoor amenities and surroundings

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

    The neuron activates on numeric or quantitative property details—measurements, counts, and number‐linked amenities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     različ
    -1.09
    udia
    -1.03
     медицин
    -1.02
     inspirasi
    -1.00
    bedür
    -1.00
    が違う
    -0.99
    exact
    -0.97
    分ほど
    -0.96
     различни
    -0.94
    かもしれない
    -0.93
    POSITIVE LOGITS
     outdoor
    1.30
     outdoors
    1.15
    ﻷ
    1.11
     views
    1.02
    둬
    1.02
    ﹪
    1.01
    ТОВ
    1.00
     учащихся
    0.99
    ﻻ
    0.99
     Empresas
    0.98
    Activations Density 0.020%

    No Known Activations