© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28623
    Prev
    Next
    INDEX
    Explanations

    weather and location descriptions

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

    The neuron fires on numerical measurements—especially meteorological figures (wind speeds, gusts, rainfall amounts, etc.).

    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
     that
    -1.48
     cukru
    -1.25
    が違う
    -1.22
     организаций
    -1.20
     предприятий
    -1.20
    Exelente
    -1.17
     protokol
    -1.16
     thousands
    -1.16
     impide
    -1.15
     jenem
    -1.15
    POSITIVE LOGITS
     will
    1.21
     Likely
    1.18
     позволит
    1.16
     and
    1.16
     дета
    1.11
    lesssim
    1.10
     GONNA
    1.09
    atization
    1.06
     olacaktır
    1.05
    よい
    1.04
    Activations Density 0.012%

    No Known Activations