© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75257
    Prev
    Next
    INDEX
    Explanations

    specific modified nouns

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

    The neuron fires on attributive adjectives—i.e. descriptive words immediately preceding a noun.

    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
    estima
    -1.44
     brosse
    -1.37
     gouverneur
    -1.36
    łgorzata
    -1.32
     gardien
    -1.32
     docteur
    -1.30
     pembunuhan
    -1.26
     président
    -1.25
    apropri
    -1.25
     mystérie
    -1.24
    POSITIVE LOGITS
     and
    1.40
    G
    1.15
    の方も
    1.13
     by
    1.12
     how
    1.08
     And
    1.06
     meeting
    1.06
    g
    1.05
     instance
    1.04
     location
    1.03
    Activations Density 0.098%

    No Known Activations