© 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. 113826
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron activates on capitalized names and titles (e.g. TV show titles, people’s names, software or license names).

    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
     vitu
    -1.67
     curent
    -1.64
     formid
    -1.48
     adver
    -1.44
     creativa
    -1.42
     recog
    -1.42
     remer
    -1.40
    ㈬
    -1.39
    ギュア
    -1.39
    ↠
    -1.38
    POSITIVE LOGITS
    อื่น
    1.77
     saying
    1.70
     Your
    1.67
     votre
    1.56
     November
    1.51
     September
    1.50
     RE
    1.47
    landır
    1.46
     fact
    1.44
     kter
    1.41
    Activations Density 0.071%

    No Known Activations