© 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. 57334
    Prev
    Next
    INDEX
    Explanations

    licensed under the

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

    This neuron strongly activates on capitalized named entities and proper nouns (e.g., person names, product titles, licenses).

    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
     gefüllt
    -0.87
    Elt
    -0.73
     appeler
    -0.73
     Honduras
    -0.72
     waistcoat
    -0.72
    ﻼ
    -0.71
     betrieben
    -0.71
     bornes
    -0.71
     BENEFITS
    -0.71
     Wheatley
    -0.71
    POSITIVE LOGITS
     Monterey
    1.09
     HBO
    1.05
    Monter
    0.83
     Sharp
    0.82
    HBO
    0.80
     Little
    0.79
    Sharp
    0.78
    Big
    0.77
    esign
    0.77
     Big
    0.75
    Activations Density 0.006%

    No Known Activations