© 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. 108302
    Prev
    Next
    INDEX
    Explanations

    paste and past forms

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

    The neuron is activated by occurrences of the substring “paste” (in any form, e.g. “paste”, “Pasted”, “pasteSpecial,” etc.).

    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
    iit
    -0.88
     Bazar
    -0.82
    äinen
    -0.82
    nante
    -0.80
     VALID
    -0.79
    however
    -0.78
     Puja
    -0.77
     boe
    -0.77
     Psal
    -0.76
     rodrigo
    -0.76
    POSITIVE LOGITS
    urized
    1.12
     tense
    1.01
     заме
    0.91
    ern
    0.86
    
    0.84
    urization
    0.79
    でん
    0.79
     Ruth
    0.79
     Jean
    0.78
     Luego
    0.78
    Activations Density 0.015%

    No Known Activations