© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127871
    Prev
    Next
    INDEX
    Explanations

    The neuron flags occurrences of words describing the source or beginning of something (e.g. “origin,” “originated”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    origin and beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     oye
    -1.06
     fati
    -1.05
    titude
    -1.02
     daly
    -1.00
     fent
    -1.00
     passat
    -0.99
     Pernambuco
    -0.99
     kue
    -0.97
     vost
    -0.96
     hond
    -0.96
    POSITIVE LOGITS
     from
    1.25
     πριν
    1.08
    toral
    1.06
    eleste
    1.02
    氏が
    0.98
    氏の
    0.96
    起源
    0.94
     añadir
    0.93
     Bevölkerung
    0.93
     dokun
    0.93
    Activations Density 0.070%

    No Known Activations