© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6920
    Prev
    Next
    INDEX
    Explanations

    Belmont, Fremont, and -mont locations

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

    The neuron activates on proper‐noun place names (toponyms) such as “Belmont,” “Fremont,” etc.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    s
    -3.00
    was
    -2.86
    is
    -2.67
    have
    -2.59
    2
    -2.58
    re
    -2.50
    as
    -2.45
    in
    -2.41
    ha
    -2.34
    y
    -2.33
    POSITIVE LOGITS
    佉
    2.84
    淠
    2.83
    ↵
    2.83
    </strong>
    2.73
    Ⲉ
    2.66
    ⬮
    2.36
    漚
    2.28
     touted
    2.28
     são
    2.25
    </sup>
    2.23
    Activations Density 0.005%

    No Known Activations