© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59192
    Prev
    Next
    INDEX
    Explanations

    Webkinz, Hotel, furniture, rares

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

    The neuron primarily detects numeric tokens (literal numbers and digits) in the text or code.

    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
    ájá
    -0.74
    endet
    -0.71
     Zweck
    -0.71
     microbiota
    -0.68
    }$}
    -0.68
     singlet
    -0.66
     kommen
    -0.66
     utilizadas
    -0.66
    amá
    -0.65
     phosphory
    -0.65
    POSITIVE LOGITS
    furn
    1.06
     furn
    1.06
     rares
    1.05
    wired
    1.00
     Hab
    0.97
     wired
    0.97
    Furn
    0.97
    Hab
    0.96
    Hotel
    0.94
    HOTEL
    0.93
    Activations Density 0.006%

    No Known Activations