© 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. 83902
    Prev
    Next
    INDEX
    Explanations

    Names and actions

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

    The neuron fires on tokens that are capitalized personal or proper names (e.g., people’s names).

    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
    }
    -3.20
    when
    -3.00
    or
    -2.80
    $
    -2.50
    dzić
    -2.47
    what
    -2.45
    hhhh
    -2.34
    there
    -2.34
    .…
    -2.34
    There
    -2.27
    POSITIVE LOGITS
    は見
    2.97
    成为了
    2.39
    をしました
    2.30
    垟
    2.28
    🗹
    2.20
    をし
    2.17
    溌
    2.16
    麁
    2.14
    を始め
    2.13
    𓁹
    2.13
    Activations Density 0.001%

    No Known Activations