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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30959
    Prev
    Next
    INDEX
    Explanations

    but WITHOUT ANY WARRANTY

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

    The neuron spotlights language from software‐license or warranty disclaimer blocks (e.g. words like “modify,” “distributed,” “but WITHOUT ANY WARRANTY,” 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
     apiece
    -0.73
     cuaca
    -0.66
    ประ
    -0.66
     Putting
    -0.65
    母親
    -0.65
     manifestó
    -0.65
     factorization
    -0.64
    route
    -0.63
     policy
    -0.63
    Putting
    -0.63
    POSITIVE LOGITS
    bbler
    0.82
    $.}
    0.77
    olive
    0.75
    bids
    0.71
    essentials
    0.71
    ()):
    0.71
    Configurator
    0.70
     Lola
    0.69
    allel
    0.67
     المح
    0.67
    Activations Density 0.047%

    No Known Activations