© 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. 16055
    Prev
    Next
    INDEX
    Explanations

    above, first, opening, explained

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

    The neuron activates on numeric tokens and sequences of 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_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
     asisten
    -1.05
     ceder
    -1.03
     triko
    -0.96
     kriminal
    -0.96
     teka
    -0.95
     palav
    -0.94
     kupa
    -0.92
     komik
    -0.91
     perle
    -0.90
     kollu
    -0.89
    POSITIVE LOGITS
     above
    1.40
     this
    1.24
    above
    1.09
     here
    0.97
    Above
    0.94
    first
    0.92
    JSONArray
    0.91
     acima
    0.90
     previous
    0.89
    𝑝
    0.88
    Activations Density 0.021%

    No Known Activations