© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33593
    Prev
    Next
    INDEX
    Explanations

    in no event liability

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

    The neuron flags terms from software‐license liability and warranty disclaimers (e.g. “no event,” “shall,” “liable,” “damages,” “provided ‘as is’”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    رو
    -0.87
    inspiring
    -0.84
    ihnachts
    -0.83
     épais
    -0.81
    Interess
    -0.79
    ایش
    -0.77
    جان
    -0.75
    ಭ
    -0.75
    現在
    -0.74
    dont
    -0.74
    POSITIVE LOGITS
     maximum
    1.42
     total
    1.10
     liability
    1.03
    Maximum
    1.00
     maximal
    1.00
    maximum
    0.97
     maksymal
    0.96
     Maximum
    0.95
     最大
    0.90
     getMax
    0.88
    Activations Density 0.036%

    No Known Activations