© 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. 34-GEMMASCOPE-RES-131K
    7. 87142
    Prev
    Next
    INDEX
    Explanations

    implied warranties including

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

    The neuron detects standard software‐license warranty‐disclaimer phrasing (e.g. “provided ‘as is’ without warranty,” “implied warranties,” “including but not limited to,” etc.).

    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
    âte
    -0.88
     sfera
    -0.82
     kalite
    -0.82
    przed
    -0.81
     nM
    -0.81
    ικών
    -0.80
     utilisant
    -0.80
     bús
    -0.80
     Faces
    -0.79
     kHz
    -0.79
    POSITIVE LOGITS
     are
    0.85
    عادة
    0.81
     workman
    0.80
     kepada
    0.80
     all
    0.77
    委会
    0.74
     дуже
    0.73
    вается
    0.73
     non
    0.73
     Oh
    0.72
    Activations Density 0.138%

    No Known Activations