© 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. 20720
    Prev
    Next
    INDEX
    Explanations

    names of media personalities

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

    The neuron fires strongly on tokens that are personal names (people’s proper names or name fragments).

    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
     many
    -1.41
     takimi
    -1.29
     various
    -1.29
    three
    -1.26
     diversas
    -1.24
     pozw
    -1.24
     successivo
    -1.24
     такие
    -1.23
     our
    -1.23
    those
    -1.22
    POSITIVE LOGITS
     htmlFor
    1.42
    aktionen
    1.34
     DANS
    1.30
     CONCENT
    1.28
     POUR
    1.28
     carbur
    1.26
     terrasse
    1.23
    ådet
    1.22
     autorisation
    1.21
    '</
    1.20
    Activations Density 0.026%

    No Known Activations