© 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. 32957
    Prev
    Next
    INDEX
    Explanations

    two car

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

    The neuron responds strongly to punctuation and discourse transitions (commas and transition words like “As”) that mark clause or sentence boundaries.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     páns
    -1.38
     civiles
    -1.38
     parachoque
    -1.34
     広場
    -1.28
     différents
    -1.27
     fiscales
    -1.27
     新款
    -1.25
    𓁹
    -1.25
     抠
    -1.23
     bluz
    -1.23
    POSITIVE LOGITS
     -
    1.34
     it
    1.29
     In
    1.28
     For
    1.27
     Only
    1.15
     It
    1.13
     If
    1.13
     ,
    1.12
     его
    1.10
     only
    1.09
    Activations Density 0.171%

    No Known Activations