© 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. 22-GEMMASCOPE-RES-131K
    7. 15820
    Prev
    Next
    INDEX
    Explanations

    adjectives describing qualities

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

    The neuron fires on unusually content‐specific or “key” tokens—words with high salience (e.g. rare or highly informative terms) in a document.

    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
    无论是
    -1.14
     addirittura
    -0.94
    不管是
    -0.92
     chứ
    -0.90
     nejen
    -0.90
     persino
    -0.88
    什么样的
    -0.87
     feuer
    -0.87
    |+\
    -0.87
    違います
    -0.86
    POSITIVE LOGITS
     but
    1.86
     like
    1.31
     some
    1.24
     nor
    1.11
     will
    1.07
     BUT
    1.06
     probably
    1.02
     Like
    1.02
     may
    1.01
     sondern
    1.00
    Activations Density 0.036%

    No Known Activations