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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69061
    Prev
    Next
    INDEX
    Explanations

    German place name endings

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

    The neuron fires on tokens containing the letter sequence “aden” (or its close variants, e.g. “oden,” “agen”).

    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
    er
    -3.33
    “
    -2.81
    z
    -2.78
    ]
    -2.70
    M
    -2.67
    K
    -2.61
    (
    -2.55
    h
    -2.38
    us
    -2.28
    T
    -2.27
    POSITIVE LOGITS
    pecabe
    2.78
     Conſ
    2.72
    ܊
    2.70
    砹
    2.67
    Kedua
    2.66
    蟜
    2.59
    쨩
    2.56
    ouſ
    2.53
     paſſ
    2.53
    说得
    2.44
    Activations Density 0.094%

    No Known Activations