© 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. 32654
    Prev
    Next
    INDEX
    Explanations

    measurement data

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

    The neuron is primarily activated by period characters (full stops), i.e. sentence-ending punctuation.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Comté
    -1.29
     också
    -1.23
     senaste
    -1.15
     thier
    -1.12
     restent
    -1.12
     största
    -1.08
     Ihren
    -1.07
     espac
    -1.05
     gjorde
    -1.05
     porcelana
    -1.05
    POSITIVE LOGITS
     skool
    1.09
     размеров
    1.08
    ,
    1.04
     star
    0.96
    It
    0.94
     ‘
    0.94
    1
    0.93
    d
    0.91
    W
    0.91
    is
    0.89
    Activations Density 0.146%

    No Known Activations