© 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. 39588
    Prev
    Next
    INDEX
    Explanations

    defined (

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

    The neuron fires on proper personal names (i.e. tokens belonging to people’s 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
    er
    -2.53
    You
    -2.28
    ra
    -2.28
    いえば
    -2.06
    言えば
    -2.00
     if
    -1.95
     suaves
    -1.91
    使った
    -1.86
     problems
    -1.82
    了你
    -1.80
    POSITIVE LOGITS
     ferrovia
    2.52
     frança
    2.42
    ’
    2.38
     gewel
    2.36
    ·
    2.25
    珦
    2.17
    '
    2.08
     feltro
    2.06
     krij
    2.05
     uniquement
    2.05
    Activations Density 0.001%

    No Known Activations