© 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. 41948
    Prev
    Next
    INDEX
    Explanations

    Liberty Counsel, Mutual, Science, ship, Police, Stadium

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

    The neuron flags occurrences of the proper noun “Liberty.”

    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
     –
    -3.02
     —
    -2.61
    会
    -2.56
     dando
    -2.44
     haupts
    -2.36
     общей
    -2.36
    D
    -2.36
    といった
    -2.33
    ar
    -2.31
    ‒
    -2.28
    POSITIVE LOGITS
    趼
    3.33
    ’
    2.81
     That
    2.81
    _{
    2.72
     It
    2.45
    呖
    2.41
    焄
    2.38
     після
    2.36
    это
    2.34
    }\
    2.33
    Activations Density 0.003%

    No Known Activations