© 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. 22-GEMMASCOPE-RES-131K
    7. 15990
    Prev
    Next
    INDEX
    Explanations

    possibility and necessity

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

    The neuron fires on modal and auxiliary constructions (words like may, will, need, must) that express possibility or necessity.

    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
     însă
    -0.97
    hield
    -0.94
    Escolha
    -0.91
     saati
    -0.91
     nữa
    -0.91
     kenyataan
    -0.89
     hiel
    -0.87
    SearchTree
    -0.85
    んですけど
    -0.85
    uestions
    -0.84
    POSITIVE LOGITS
     will
    1.27
     they
    1.21
     might
    1.12
     sometimes
    1.09
     may
    1.09
    อาจ
    1.03
     często
    1.01
    可能会
    1.00
     often
    0.99
     WILL
    0.98
    Activations Density 0.019%

    No Known Activations