© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66390
    Prev
    Next
    INDEX
    Explanations

    expulsion, eviction, deportation

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

    The neuron detects words (and related forms) that express forced removal or expulsion (e.g. “kicked out,” “expelled,” “evicted,” “expulsion”).

    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
     doubtless
    -1.49
    omethane
    -1.48
     fulfil
    -1.47
    ні
    -1.44
    手に
    -1.39
     organise
    -1.38
    ⢪
    -1.37
     confirma
    -1.34
     wzglę
    -1.34
     influencia
    -1.34
    POSITIVE LOGITS
    ("")
    1.75
    ൅
    1.72
    imageName
    1.57
    两个
    1.55
    edere
    1.51
    ’).
    1.49
    鬭
    1.48
    vete
    1.43
    cún
    1.41
    breviations
    1.40
    Activations Density 0.018%

    No Known Activations