© 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. 35488
    Prev
    Next
    INDEX
    Explanations

    brands and items

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

    The neuron activates on capitalized words or names—that is, proper nouns and named entities.

    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
     which
    -1.56
     that
    -1.38
     mengganggu
    -1.13
     whose
    -1.09
     want
    -1.05
     besonders
    -1.02
     particularly
    -0.97
     helping
    -0.96
     will
    -0.96
     wanted
    -0.94
    POSITIVE LOGITS
     Weitere
    1.07
     sowieso
    1.06
    several
    1.05
     многих
    1.03
    oires
    1.02
     использовании
    1.02
     большин
    1.00
    obviously
    1.00
    atize
    1.00
    tocks
    0.98
    Activations Density 0.088%

    No Known Activations