© 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. 106537
    Prev
    Next
    INDEX
    Explanations

    the followed by a noun

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

    This neuron fires on tokens that are long numeric values (multi-digit numbers, especially three or more digits).

    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
    AMENT
    -1.26
    nesses
    -1.05
    BURGH
    -1.03
    向了
    -1.01
    imetric
    -1.00
    )**
    -0.98
    Ｍ
    -0.97
    caping
    -0.94
    GGGG
    -0.93
    hoto
    -0.93
    POSITIVE LOGITS
     it
    1.77
     resulting
    1.20
     endeavor
    1.20
     farlo
    1.19
     effort
    1.18
     situation
    1.18
     occasion
    1.15
    zembro
    1.15
    葙
    1.09
    pergillus
    1.09
    Activations Density 0.112%

    No Known Activations