© 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. 24981
    Prev
    Next
    INDEX
    Explanations

    agreement or confirmation

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

    The neuron flags sentence boundaries, firing strongly on sentence-ending punctuation and the first word of the next sentence.

    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
    和平
    -0.93
    <u>
    -0.93
     and
    -0.89
    MK
    -0.89
     it
    -0.88
    knowledge
    -0.86
    ̶
    -0.85
    ējās
    -0.85
     internationales
    -0.84
     Distillery
    -0.83
    POSITIVE LOGITS
     Speaking
    0.93
     Indeed
    0.90
     действительно
    0.89
     actually
    0.86
    Speaking
    0.85
     again
    0.85
     Infatti
    0.83
    이버
    0.81
    そちら
    0.81
     proprement
    0.78
    Activations Density 0.030%

    No Known Activations