© 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. 10-GEMMASCOPE-RES-131K
    7. 44651
    Prev
    Next
    INDEX
    Explanations

    entities and concepts

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

    The neuron selectively fires on prominent domain‐specific content nouns that name the main subject or topic of the text.

    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
     it
    -1.35
    s
    -1.16
     you
    -1.12
     légales
    -1.02
    Dados
    -1.02
    GetAxis
    -1.02
     роки
    -1.01
     we
    -1.00
    Carreira
    -1.00
    Reparto
    -0.99
    POSITIVE LOGITS
    一個
    1.48
    一种
    1.34
    能够
    1.34
    lenen
    1.31
    bản
    1.29
    一些
    1.28
    一个
    1.28
    小さい
    1.27
     используют
    1.26
    wieder
    1.25
    Activations Density 0.160%

    No Known Activations