© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10483
    Prev
    Next
    INDEX
    Explanations

    Berger, Pedro, unistd

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

    the name "Berger" or similar surnames, particularly in formal contexts like legal documents, academic citations, and author credits.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of personal proper names (e.g. first or last names).

    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
    ਲ਼
    -2.42
    玉石
    -2.33
     Они
    -2.33
     間取り
    -2.25
    лізу
    -2.22
     剤
    -2.14
     adanya
    -2.13
     tetapi
    -2.13
    柔和
    -2.13
    This
    -2.11
    POSITIVE LOGITS
     I
    2.67
    抺
    2.14
     つの
    2.14
     сказал
    2.13
    嚷
    2.05
     杯
    2.03
    pecabe
    2.02
    ︲
    1.95
    旁边的
    1.95
     她
    1.92
    Activations Density 0.002%

    No Known Activations