© 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. 25653
    Prev
    Next
    INDEX
    Explanations

    will be

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

    The neuron fires on future‐tense constructions—particularly the modal “will” (and its contraction ’ll) plus accompanying auxiliary verbs.

    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
     banyak
    -1.05
    Melhor
    -1.02
    Conheça
    -1.00
    ʬ
    -0.99
     bestand
    -0.97
    onymus
    -0.96
     Offisielt
    -0.96
    apture
    -0.96
     nhiều
    -0.96
    我们的
    -0.96
    POSITIVE LOGITS
     automatically
    1.80
     will
    1.79
     your
    1.33
     you
    1.29
     automatic
    1.16
     €/
    1.15
     automatiquement
    1.14
     they
    1.04
     自動
    1.03
     separa
    1.03
    Activations Density 0.169%

    No Known Activations