© 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. 26343
    Prev
    Next
    INDEX
    Explanations

    verses and citations

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

    The neuron strongly activates on numeric tokens—especially digits and chapter‐verse patterns—so it’s looking for numbers (e.g. verse references).

    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
    pullover
    -1.13
    お待ちしております
    -1.10
    playmobil
    -1.09
    salomon
    -1.09
     romantis
    -1.06
     mahu
    -1.06
     foton
    -1.05
    pneu
    -1.05
     kreativ
    -1.04
     två
    -1.03
    POSITIVE LOGITS
    1
    1.21
    5
    1.19
    7
    1.18
     צריך
    1.02
     idade
    1.02
     should
    1.01
    Es
    0.98
    8
    0.98
    av
    0.96
    9
    0.96
    Activations Density 0.001%

    No Known Activations