© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117047
    Prev
    Next
    INDEX
    Explanations

    software version numbers

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

    The neuron activates on numeric tokens—especially version numbers or other digit sequences in the text.

    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
    onces
    -1.09
     Vö
    -1.03
    eaways
    -1.02
     KELLY
    -1.00
    ālā
    -0.99
    ≅
    -0.99
    })->
    -0.97
    ＄
    -0.96
    ⊗
    -0.93
    ⅞
    -0.93
    POSITIVE LOGITS
     verschiedenen
    1.07
     ferramenta
    1.02
    Kunden
    0.98
    ętr
    0.92
    Instrucciones
    0.91
     pneumoniae
    0.91
     nurt
    0.88
     Produkten
    0.88
     diversas
    0.84
     zahlreichen
    0.84
    Activations Density 0.092%

    No Known Activations