© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64472
    Prev
    Next
    INDEX
    Explanations

    locations of stores, delis, and ads

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

    The neuron fires on sequences of digits or numeric tokens.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    calciatore
    -1.16
     first
    -1.15
     
    -1.13
     only
    -1.05
     conhe
    -1.05
     xmlns
    -1.02
     three
    -1.02
    häuse
    -1.01
    llywood
    -1.00
    opheles
    -0.97
    POSITIVE LOGITS
    weich
    1.13
    melada
    0.99
    ?”.
    0.95
     solidari
    0.95
    Apoll
    0.95
    DDG
    0.94
     pavilion
    0.93
    ⢠
    0.93
    えず
    0.93
     battu
    0.93
    Activations Density 0.002%

    No Known Activations