© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71054
    Prev
    Next
    INDEX
    Explanations

    for any

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

    The neuron specializes in picking up words from legal liability‐disclaimer passages (e.g. “in no event shall … be liable for any damages or other liability…”).

    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
     also
    -1.32
     this
    -1.25
     our
    -1.20
     your
    -1.15
     declarado
    -1.08
    такт
    -1.02
     redan
    -1.00
     colega
    -1.00
     Ayrıca
    -1.00
     společnosti
    -0.98
    POSITIVE LOGITS
    ,
    1.21
     который
    1.02
    They
    0.99
    那么
    0.98
    хи
    0.98
     habari
    0.98
    import
    0.97
    之为
    0.96
     которая
    0.96
     　　
    0.94
    Activations Density 0.027%

    No Known Activations