© 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. 22-GEMMASCOPE-RES-131K
    7. 15146
    Prev
    Next
    INDEX
    Explanations

    academic journal titles and article metadata

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

    This neuron detects the end of academic paper titles in reference entries (i.e., the period or marker at the close of a bibliographic title line).

    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
     it
    -1.03
     will
    -1.02
     of
    -0.99
    被告
    -0.90
    再度
    -0.85
     Strafe
    -0.85
     being
    -0.83
     had
    -0.79
     betre
    -0.78
     nacional
    -0.77
    POSITIVE LOGITS
     dépens
    1.15
     például
    1.07
     perdió
    1.06
     mostró
    1.04
     reveló
    1.02
     akár
    1.02
    okkal
    1.01
     réjou
    0.97
    Dont
    0.96
     naprawdę
    0.96
    Activations Density 0.068%

    No Known Activations