© 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. 10-GEMMASCOPE-RES-131K
    7. 13815
    Prev
    Next
    INDEX
    Explanations

    famous names and titles

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

    The neuron strongly activates on proper names of creative works (titles of books, films, TV shows, etc.).

    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
     that
    -1.48
     jejich
    -1.43
     muualla
    -1.40
     THOSE
    -1.40
     baada
    -1.37
     those
    -1.36
     their
    -1.34
     THEIR
    -1.34
     تقوم
    -1.32
    actéris
    -1.27
    POSITIVE LOGITS
    <td>
    1.19
    цией
    1.18
    сти
    1.09
    paired
    1.06
    Па
    1.04
     традиции
    1.04
    astanza
    1.04
    orsese
    1.04
    इन
    1.04
    Се
    1.03
    Activations Density 0.022%

    No Known Activations