© 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. 34-GEMMASCOPE-RES-131K
    7. 106435
    Prev
    Next
    INDEX
    Explanations

    sentence endings

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

    The neuron is acting like a running token-position counter, steadily increasing its activation as you move further into the text.

    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
    hibitions
    -1.05
     millón
    -0.95
    fahrzeuge
    -0.88
    vertebrates
    -0.88
    (';
    -0.88
    Ť
    -0.87
    }})
    -0.87
    Ö
    -0.87
     راست
    -0.86
     विशेष
    -0.86
    POSITIVE LOGITS
     this
    1.55
     also
    1.30
     Needless
    1.29
     very
    1.29
     then
    1.28
    Needless
    1.16
     so
    1.16
     очень
    1.15
     Additionally
    1.12
    完成です
    1.11
    Activations Density 0.019%

    No Known Activations