© 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. 22-GEMMASCOPE-RES-131K
    7. 39588
    Prev
    Next
    INDEX
    Explanations

    warranty or merchantability

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

    The neuron activates on legal‐disclaimer jargon, particularly warranty, liability, and software suitability terms in license or disclaimer statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ⩕
    -1.01
    และ
    -1.01
    ⢅
    -0.99
     Anwendungs
    -0.98
     гораздо
    -0.98
     embreagem
    -0.98
     Vorgang
    -0.96
     соответству
    -0.95
     instead
    -0.94
     bañera
    -0.94
    POSITIVE LOGITS
     or
    1.75
    脍
    1.44
     will
    1.27
     nor
    1.24
    谆
    1.17
     any
    1.17
     which
    1.15
    😫
    1.13
     may
    1.11
    🥹
    1.11
    Activations Density 0.042%

    No Known Activations