© 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. 34-GEMMASCOPE-RES-131K
    7. 58724
    Prev
    Next
    INDEX
    Explanations

    negative or controversial concepts

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

    This neuron responds selectively to Latinate words.

    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
     of
    -1.24
     considerado
    -1.03
    considered
    -1.02
     considerada
    -1.00
    S
    -0.99
     mellett
    -0.97
     Considered
    -0.97
     I
    -0.95
     lẫn
    -0.95
    D
    -0.92
    POSITIVE LOGITS
     because
    2.05
     worthy
    1.75
     when
    1.75
     even
    1.72
     while
    1.51
    because
    1.50
    worthy
    1.42
     despite
    1.41
     unworthy
    1.31
     çünkü
    1.30
    Activations Density 0.096%

    No Known Activations