© 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. 127673
    Prev
    Next
    INDEX
    Explanations

    pronoun or preposition followed by noun

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

    The neuron broadly activates on common, high‐frequency English words (e.g. simple verbs, pronouns, conjunctions, and other everyday vocabulary).

    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
     its
    -1.34
    :
    -1.34
    /
    -1.30
    ;
    -1.30
     []:
    -1.30
     to
    -1.25
     behauptet
    -1.24
     '\\;'
    -1.23
     currently
    -1.23
         
    -1.23
    POSITIVE LOGITS
     there
    1.74
    这里的
    1.36
     they
    1.36
    Meskipun
    1.36
     menyadari
    1.35
    を書いて
    1.33
    鱟
    1.33
     about
    1.33
     они
    1.32
    他們
    1.32
    Activations Density 0.161%

    No Known Activations