© 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. 10-GEMMASCOPE-RES-131K
    7. 21217
    Prev
    Next
    INDEX
    Explanations

    consecutive events or periods

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

    The neuron primarily detects the word “straight” when used to denote consecutive occurrences or runs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    {
    -2.72
    ↵↵
    -2.17
     Â
    -2.06
     теми
    -2.06
    .
    -2.03
    </strong>
    -1.86
    \
    -1.83
    に行って
    -1.81
    -
    -1.80
    将他
    -1.77
    POSITIVE LOGITS
     paradiso
    2.09
     potes
    2.03
     spela
    2.02
    婓
    1.98
     Mère
    1.96
     ritratto
    1.89
    緜
    1.87
     albero
    1.86
     dipinto
    1.81
    쫀
    1.81
    Activations Density 0.009%

    No Known Activations