© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31420
    Prev
    Next
    INDEX
    Explanations

    reaching a culmination or conclusion

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

    This neuron fires on occurrences of the verb “reached” (and closely associated tokens) signaling attainment of a level or milestone.

    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
    何か
    -1.07
    媄
    -1.05
     они
    -1.05
    ⡶
    -1.04
    玊
    -1.01
     razor
    -0.98
    ディオ
    -0.98
     οπο
    -0.97
     вашего
    -0.97
    蹴
    -0.95
    POSITIVE LOGITS
     into
    1.88
     the
    1.68
     fruition
    1.51
     adulthood
    1.38
    ieve
    1.34
     to
    1.24
     maturity
    1.16
     orgasm
    1.13
     saturation
    1.09
    Conclusion
    1.08
    Activations Density 0.021%

    No Known Activations