© 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. 10-GEMMASCOPE-RES-131K
    7. 60893
    Prev
    Next
    INDEX
    Explanations

    academic paper abstract

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

    This neuron fires on tokens marking the start of an article’s abstract or summary section.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    junctive
    -1.59
     anadolu
    -1.56
     vulgares
    -1.56
     "@
    -1.55
    ዖ
    -1.53
     хоте
    -1.52
     españa
    -1.51
     pensamentos
    -1.48
     multicolore
    -1.48
    䨻
    -1.46
    POSITIVE LOGITS
     without
    1.60
     our
    1.48
    友人
    1.45
     from
    1.45
     оптима
    1.43
     übri
    1.41
     seperti
    1.38
     tweaking
    1.38
     through
    1.37
    我已经
    1.35
    Activations Density 0.026%

    No Known Activations