© 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. 34-GEMMASCOPE-RES-131K
    7. 107313
    Prev
    Next
    INDEX
    Explanations

    names starting with edel, eden, edin

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

    The neuron strongly activates on any token containing the letter sequence “edi.”

    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
    LING
    -0.85
    րի
    -0.81
     jantar
    -0.78
    DHCP
    -0.78
    În
    -0.78
    نر
    -0.77
     corazón
    -0.77
    Enumerated
    -0.76
    duced
    -0.74
    砰
    -0.74
    POSITIVE LOGITS
    繁
    0.77
     clues
    0.69
    abba
    0.66
    india
    0.66
     clue
    0.66
     man
    0.65
     worry
    0.65
    }^{-\
    0.64
    Mug
    0.63
    Billie
    0.63
    Activations Density 0.024%

    No Known Activations