© 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. 22-GEMMASCOPE-RES-131K
    7. 27252
    Prev
    Next
    INDEX
    Explanations

    proper nouns or brand names

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

    The neuron fires strongly on capitalized proper nouns—names of people, places, or organizations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     but
    -1.40
     otros
    -1.33
     envol
    -1.32
    erunner
    -1.31
    𝟭
    -1.30
    áis
    -1.30
    ########.
    -1.27
     Isso
    -1.26
     וכן
    -1.26
     corrispond
    -1.24
    POSITIVE LOGITS
     is
    1.84
    2
    1.73
    1
    1.59
     wasn
    1.55
     has
    1.54
     had
    1.44
    4
    1.44
    가
    1.33
    5
    1.32
    が
    1.32
    Activations Density 0.126%

    No Known Activations