© 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. 92814
    Prev
    Next
    INDEX
    Explanations

    due to / spite of / ended up

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

    This neuron fires on stretches of self-referential, first-person narrative (personal anecdotes and “I…” statements).

    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
     السياس
    -1.21
     resep
    -1.13
     vasi
    -1.05
     furg
    -1.04
     фанта
    -1.04
    ________
    -1.04
    LEY
    -1.03
    ଵ
    -1.03
     ikon
    -1.02
     dolo
    -1.02
    POSITIVE LOGITS
     trough
    1.36
     „
    1.22
     cariño
    1.18
    Nr
    1.13
     nr
    1.10
     ideias
    1.10
    lenght
    1.05
     dunno
    1.05
     ибо
    1.03
     albeit
    1.02
    Activations Density 0.448%

    No Known Activations