© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99345
    Prev
    Next
    INDEX
    Explanations

    immigrant or immigrants

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

    The neuron selectively activates on occurrences of the word “immigrant” (and its plural or compound forms) in the text.

    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
     hochwer
    -2.52
     he
    -2.50
     которые
    -2.48
    ーーー
    -2.44
     $
    -2.39
    Ă
    -2.34
    ーー
    -2.34
    "-
    -2.33
    ي
    -2.28
    </strong>
    -2.25
    POSITIVE LOGITS
    𖥧
    2.72
    鲮
    2.67
     Then
    2.53
    спомина
    2.52
    żą
    2.47
    ㌘
    2.41
     ané
    2.39
    ’，
    2.36
     After
    2.34
     Instead
    2.30
    Activations Density 0.003%

    No Known Activations