© 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. 110853
    Prev
    Next
    INDEX
    Explanations

    code prefixes like #, copy,

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

    The neuron is specialized to detect numeric literals (numbers) 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
    浙
    -0.69
     tratamientos
    -0.67
     caer
    -0.64
    Nt
    -0.63
    Nw
    -0.63
     Jenn
    -0.63
     forced
    -0.63
     aprile
    -0.63
     Remote
    -0.62
     vientos
    -0.62
    POSITIVE LOGITS
    অ
    0.84
    ερ
    0.69
    zón
    0.69
    }]$
    0.69
    wnątrz
    0.68
     licensing
    0.66
    トンネル
    0.66
     MDM
    0.66
    Tē
    0.66
    Για
    0.66
    Activations Density 0.053%

    No Known Activations