© 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. 34-GEMMASCOPE-RES-131K
    7. 77402
    Prev
    Next
    INDEX
    Explanations

    pronouns that perform states or actions

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

    The neuron is mainly triggered by parenthetical constructions (the “(” and “)” tokens and their contents).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    一旁的
    -1.09
    igshid
    -0.91
    pptx
    -0.90
    NUMX
    -0.88
    icône
    -0.86
     Ernährung
    -0.85
    envoi
    -0.84
     Estas
    -0.82
    mr
    -0.81
    竟然是
    -0.81
    POSITIVE LOGITS
     he
    2.98
     s
    2.81
     him
    2.42
     she
    2.42
     they
    2.27
     ему
    1.91
    他
    1.83
     он
    1.80
    เค้า
    1.59
     egli
    1.58
    Activations Density 0.097%

    No Known Activations