© 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. 34306
    Prev
    Next
    INDEX
    Explanations

    all or total sums

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

    This neuron activates on four-digit numeric tokens representing model years (dates).

    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
    猙
    -1.08
     courriel
    -1.07
    $
    -1.06
    despite
    -1.03
     estamp
    -1.03
    albeit
    -1.03
     poiv
    -1.02
     occuper
    -1.01
     monstruos
    -1.01
    病例
    -1.00
    POSITIVE LOGITS
     all
    1.41
     each
    1.27
     total
    1.23
    其中
    1.19
     average
    1.15
     with
    1.13
     overall
    1.13
     averages
    1.08
     ALL
    1.05
     went
    1.04
    Activations Density 0.004%

    No Known Activations