© 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. 10-GEMMASCOPE-RES-131K
    7. 48118
    Prev
    Next
    INDEX
    Explanations

    lots and property sales

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

    The neuron fires on numeric quantity tokens—especially decimal measurements (e.g. lot sizes, dimensions, prices).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     lèvres
    -2.25
     Etat
    -2.16
     antena
    -2.09
    鲣
    -2.06
     apartament
    -2.03
     passat
    -2.00
     appartement
    -2.00
     velours
    -1.98
     wali
    -1.98
     oorsp
    -1.97
    POSITIVE LOGITS
    '
    2.91
    \
    2.25
    2
    2.17
     '
    2.09
     hastily
    1.98
    ('
    1.95
    -
    1.93
    "
    1.92
    as
    1.88
    ות
    1.84
    Activations Density 0.004%

    No Known Activations